diff --git "a/profile_trace/iteration_32256/rank4_trace.json" "b/profile_trace/iteration_32256/rank4_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_32256/rank4_trace.json" @@ -0,0 +1,157273 @@ + +{ + "schemaVersion": 1, + "deviceProperties": [ + { + "id": 0, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 1, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 2, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 3, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 4, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 5, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 6, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 7, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + } + ], + "cupti_version": 22, + "cuda_runtime_version": 12040, + "cuda_driver_version": 12080, + "distributedInfo": {"backend": "nccl", "rank": 4, "world_size": 8, "pg_count": 1, "pg_config": [{"pg_name": "0", "pg_desc": "default_pg", "backend_config": "cuda:nccl", "pg_size": 8, "ranks": [0, 1, 2, 3, 4, 5, 6, 7]}], "nccl_version": "2.21.5"}, + "record_shapes": 1, + "trace_id": "0D91CCB4375848B897A0CD9A445D943B", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531351951.576, "dur": 191.326, + "args": { + "External id": 1407489,"Record function id": 0, "Sequence number": 15109068, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531351974.152, "dur": 156.512, + "args": { + "External id": 1407490,"Sequence number": 15109068, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 1 + } + }, + { + "ph": "f", "id": 1, "pid": 2338710, "tid": 2379450, "ts": 6410531351974.152, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338710, "tid": 2379450, + "ts": 6410531351984.133, "dur": 143.304, + "args": { + "External id": 1407491,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 2 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531352160.947, "dur": 318.580, + "args": { + "External id": 1407492,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531352233.640, "dur": 118.228, + "args": { + "External id": 1407493,"Record function id": 0, "Ev Idx": 4 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.25", "pid": 2338710, "tid": 2379450, + "ts": 6410531352273.700, "dur": 64.202, + "args": { + "External id": 1407494,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531352358.497, "dur": 2.761, + "args": { + "External id": 1407495,"Sequence number": 15109067, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 6 + } + }, + { + "ph": "f", "id": 2, "pid": 2338710, "tid": 2379450, "ts": 6410531352358.497, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531352367.987, "dur": 102.620, + "args": { + "External id": 1407496,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 7 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531352381.860, "dur": 87.699, + "args": { + "External id": 1407497,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 8 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531352396.845, "dur": 4.489, + "args": { + "External id": 1407498,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531352493.136, "dur": 38269.311, + "args": { + "External id": 1407499,"Record function id": 0, "Sequence number": 15109065, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531352495.630, "dur": 38247.072, + "args": { + "External id": 1407500,"Sequence number": 15109065, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11 + } + }, + { + "ph": "f", "id": 3, "pid": 2338710, "tid": 2379450, "ts": 6410531352495.630, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531352554.404, "dur": 4.736, + "args": { + "External id": 1407501,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531352566.496, "dur": 37780.490, + "args": { + "External id": 1407502,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531352568.990, "dur": 37777.443, + "args": { + "External id": 1407503,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 14 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531352575.974, "dur": 7.211, + "args": { + "External id": 1407504,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531352585.660, "dur": 37758.261, + "args": { + "External id": 1407505,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 16 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338710, "tid": 2379450, + "ts": 6410531390354.326, "dur": 0.807, + "args": { + "External id": 1407506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 17 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410531390358.381, "dur": 4.167, + "args": { + "External id": 1407507,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 18 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410531390360.849, "dur": 1.549, + "args": { + "External id": 1407508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2379450, + "ts": 6410531390371.900, "dur": 55.097, + "args": { + "External id": 1407509,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 20 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2379450, + "ts": 6410531390439.068, "dur": 59.353, + "args": { + "External id": 1407510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2379450, + "ts": 6410531390441.532, "dur": 56.645, + "args": { + "External id": 1407511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 22 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2379450, + "ts": 6410531390444.141, "dur": 53.560, + "args": { + "External id": 1407512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 23 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531390782.795, "dur": 28.080, + "args": { + "External id": 1407513,"Record function id": 0, "Sequence number": 15109064, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531390785.647, "dur": 20.552, + "args": { + "External id": 1407514,"Sequence number": 15109064, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 25 + } + }, + { + "ph": "f", "id": 4, "pid": 2338710, "tid": 2379450, "ts": 6410531390785.647, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531390792.499, "dur": 13.413, + "args": { + "External id": 1407515,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 26 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531390798.982, "dur": 6.728, + "args": { + "External id": 1407516,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 27 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531390818.184, "dur": 144.799, + "args": { + "External id": 1407517,"Record function id": 0, "Sequence number": 15109063, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531390819.278, "dur": 134.467, + "args": { + "External id": 1407518,"Sequence number": 15109063, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 29 + } + }, + { + "ph": "f", "id": 5, "pid": 2338710, "tid": 2379450, "ts": 6410531390819.278, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531390823.582, "dur": 129.416, + "args": { + "External id": 1407519,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 30 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531390831.020, "dur": 48.828, + "args": { + "External id": 1407520,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 31 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531390836.523, "dur": 9.176, + "args": { + "External id": 1407521,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 32 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531390848.720, "dur": 30.779, + "args": { + "External id": 1407522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 33 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531390852.755, "dur": 26.309, + "args": { + "External id": 1407523,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 34 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531390886.579, "dur": 5.634, + "args": { + "External id": 1407524,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 35 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531390890.017, "dur": 1.781, + "args": { + "External id": 1407525,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 36 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531390894.161, "dur": 57.890, + "args": { + "External id": 1407526,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 37 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531390968.678, "dur": 77.828, + "args": { + "External id": 1407527,"Record function id": 0, "Sequence number": 15109062, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531390970.506, "dur": 71.121, + "args": { + "External id": 1407528,"Sequence number": 15109062, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 39 + } + }, + { + "ph": "f", "id": 6, "pid": 2338710, "tid": 2379450, "ts": 6410531390970.506, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531390974.094, "dur": 67.128, + "args": { + "External id": 1407529,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "3"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 40 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531390979.982, "dur": 24.004, + "args": { + "External id": 1407530,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 41 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531390981.653, "dur": 3.810, + "args": { + "External id": 1407531,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 42 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531390986.516, "dur": 17.152, + "args": { + "External id": 1407532,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 43 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531390990.821, "dur": 12.340, + "args": { + "External id": 1407533,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 44 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410531391006.255, "dur": 9.629, + "args": { + "External id": 1407534,"Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 45 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531391013.478, "dur": 1.550, + "args": { + "External id": 1407535,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 46 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531391016.835, "dur": 23.741, + "args": { + "External id": 1407536,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 47 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531391051.202, "dur": 309.122, + "args": { + "External id": 1407537,"Record function id": 0, "Sequence number": 15109061, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531391088.708, "dur": 264.595, + "args": { + "External id": 1407538,"Sequence number": 15109061, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 49 + } + }, + { + "ph": "f", "id": 7, "pid": 2338710, "tid": 2379450, "ts": 6410531391088.708, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531391095.056, "dur": 257.668, + "args": { + "External id": 1407539,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 50 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531391100.433, "dur": 30.811, + "args": { + "External id": 1407540,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 51 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531391101.705, "dur": 7.874, + "args": { + "External id": 1407541,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 52 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531391110.796, "dur": 20.147, + "args": { + "External id": 1407542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 53 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531391112.320, "dur": 18.103, + "args": { + "External id": 1407543,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 54 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531391132.700, "dur": 3.194, + "args": { + "External id": 1407544,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 55 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531391134.345, "dur": 1.178, + "args": { + "External id": 1407545,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 56 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531391140.099, "dur": 210.991, + "args": { + "External id": 1407546,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 57 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531391368.325, "dur": 114.452, + "args": { + "External id": 1407547,"Record function id": 0, "Sequence number": 15109060, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531391369.997, "dur": 106.121, + "args": { + "External id": 1407548,"Sequence number": 15109060, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 59 + } + }, + { + "ph": "f", "id": 8, "pid": 2338710, "tid": 2379450, "ts": 6410531391369.997, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531391372.055, "dur": 103.508, + "args": { + "External id": 1407549,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 60 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531391376.232, "dur": 18.047, + "args": { + "External id": 1407550,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 61 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531391377.293, "dur": 2.655, + "args": { + "External id": 1407551,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 62 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531391381.032, "dur": 12.971, + "args": { + "External id": 1407552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 63 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531391382.005, "dur": 11.514, + "args": { + "External id": 1407553,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 64 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531391395.649, "dur": 4.364, + "args": { + "External id": 1407554,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 65 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531391399.093, "dur": 0.677, + "args": { + "External id": 1407555,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 66 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531391401.374, "dur": 72.609, + "args": { + "External id": 1407556,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 67 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531391493.940, "dur": 49.958, + "args": { + "External id": 1407557,"Record function id": 0, "Sequence number": 15109059, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531391495.708, "dur": 1.435, + "args": { + "External id": 1407558,"Sequence number": 15109059, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 69 + } + }, + { + "ph": "f", "id": 9, "pid": 2338710, "tid": 2379450, "ts": 6410531391495.708, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531391500.839, "dur": 38.164, + "args": { + "External id": 1407559,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 70 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531391503.975, "dur": 34.273, + "args": { + "External id": 1407560,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 71 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531391516.552, "dur": 0.881, + "args": { + "External id": 1407561,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 72 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531391550.170, "dur": 2300.074, + "args": { + "External id": 1407562,"Record function id": 0, "Sequence number": 15109057, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531391552.299, "dur": 2252.049, + "args": { + "External id": 1407563,"Sequence number": 15109057, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 74 + } + }, + { + "ph": "f", "id": 10, "pid": 2338710, "tid": 2379450, "ts": 6410531391552.299, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531391602.867, "dur": 3.651, + "args": { + "External id": 1407564,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 75 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531391609.729, "dur": 1932.258, + "args": { + "External id": 1407565,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 76 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531391611.974, "dur": 1929.639, + "args": { + "External id": 1407566,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 77 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531391615.373, "dur": 7.032, + "args": { + "External id": 1407567,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 78 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531391623.458, "dur": 1916.857, + "args": { + "External id": 1407568,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 79 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338710, "tid": 2379450, + "ts": 6410531393546.496, "dur": 0.683, + "args": { + "External id": 1407569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 80 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410531393549.108, "dur": 5.784, + "args": { + "External id": 1407570,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 81 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410531393553.490, "dur": 1.204, + "args": { + "External id": 1407571,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 82 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2379450, + "ts": 6410531393560.298, "dur": 27.815, + "args": { + "External id": 1407572,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 83 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2379450, + "ts": 6410531393594.747, "dur": 46.985, + "args": { + "External id": 1407573,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 84 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2379450, + "ts": 6410531393596.023, "dur": 45.455, + "args": { + "External id": 1407574,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 85 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2379450, + "ts": 6410531393597.534, "dur": 43.619, + "args": { + "External id": 1407575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 86 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531393820.901, "dur": 24.048, + "args": { + "External id": 1407576,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 87 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531393862.769, "dur": 21.251, + "args": { + "External id": 1407577,"Record function id": 0, "Sequence number": 15109056, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531393864.888, "dur": 15.038, + "args": { + "External id": 1407578,"Sequence number": 15109056, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 89 + } + }, + { + "ph": "f", "id": 11, "pid": 2338710, "tid": 2379450, "ts": 6410531393864.888, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531393872.591, "dur": 7.069, + "args": { + "External id": 1407579,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 90 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531393874.127, "dur": 5.324, + "args": { + "External id": 1407580,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 91 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531393888.374, "dur": 96.465, + "args": { + "External id": 1407581,"Record function id": 0, "Sequence number": 15109055, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531393889.532, "dur": 89.342, + "args": { + "External id": 1407582,"Sequence number": 15109055, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 93 + } + }, + { + "ph": "f", "id": 12, "pid": 2338710, "tid": 2379450, "ts": 6410531393889.532, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531393892.194, "dur": 86.316, + "args": { + "External id": 1407583,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 94 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531393900.827, "dur": 24.921, + "args": { + "External id": 1407584,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 95 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531393903.165, "dur": 3.987, + "args": { + "External id": 1407585,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 96 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531393908.218, "dur": 17.217, + "args": { + "External id": 1407586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 97 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531393910.241, "dur": 14.739, + "args": { + "External id": 1407587,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 98 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531393927.734, "dur": 3.948, + "args": { + "External id": 1407588,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 99 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531393930.138, "dur": 1.133, + "args": { + "External id": 1407589,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531393932.966, "dur": 44.604, + "args": { + "External id": 1407590,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531393990.350, "dur": 143.073, + "args": { + "External id": 1407591,"Record function id": 0, "Sequence number": 15109054, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531393991.832, "dur": 135.928, + "args": { + "External id": 1407592,"Sequence number": 15109054, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 103 + } + }, + { + "ph": "f", "id": 13, "pid": 2338710, "tid": 2379450, "ts": 6410531393991.832, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531393997.567, "dur": 129.592, + "args": { + "External id": 1407593,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "2"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531394000.063, "dur": 25.752, + "args": { + "External id": 1407594,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531394001.221, "dur": 3.148, + "args": { + "External id": 1407595,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394008.124, "dur": 17.378, + "args": { + "External id": 1407596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394009.070, "dur": 15.977, + "args": { + "External id": 1407597,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410531394027.288, "dur": 10.991, + "args": { + "External id": 1407598,"Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531394033.642, "dur": 4.078, + "args": { + "External id": 1407599,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394039.108, "dur": 86.520, + "args": { + "External id": 1407600,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531394144.485, "dur": 163.656, + "args": { + "External id": 1407601,"Record function id": 0, "Sequence number": 15109053, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531394146.174, "dur": 156.622, + "args": { + "External id": 1407602,"Sequence number": 15109053, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 113 + } + }, + { + "ph": "f", "id": 14, "pid": 2338710, "tid": 2379450, "ts": 6410531394146.174, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531394149.564, "dur": 152.726, + "args": { + "External id": 1407603,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531394151.628, "dur": 28.556, + "args": { + "External id": 1407604,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531394153.352, "dur": 3.468, + "args": { + "External id": 1407605,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394160.475, "dur": 19.387, + "args": { + "External id": 1407606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394162.109, "dur": 17.215, + "args": { + "External id": 1407607,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531394181.815, "dur": 5.915, + "args": { + "External id": 1407608,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531394186.051, "dur": 1.369, + "args": { + "External id": 1407609,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394188.689, "dur": 112.455, + "args": { + "External id": 1407610,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531394313.945, "dur": 146.266, + "args": { + "External id": 1407611,"Record function id": 0, "Sequence number": 15109052, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531394315.400, "dur": 116.149, + "args": { + "External id": 1407612,"Sequence number": 15109052, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 123 + } + }, + { + "ph": "f", "id": 15, "pid": 2338710, "tid": 2379450, "ts": 6410531394315.400, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531394319.863, "dur": 111.246, + "args": { + "External id": 1407613,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531394321.182, "dur": 22.213, + "args": { + "External id": 1407614,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531394322.261, "dur": 2.700, + "args": { + "External id": 1407615,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394325.962, "dur": 17.138, + "args": { + "External id": 1407616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394329.677, "dur": 12.943, + "args": { + "External id": 1407617,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531394344.581, "dur": 2.528, + "args": { + "External id": 1407618,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531394346.343, "dur": 0.574, + "args": { + "External id": 1407619,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394348.066, "dur": 81.542, + "args": { + "External id": 1407620,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394439.296, "dur": 19.124, + "args": { + "External id": 1407621,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531394468.029, "dur": 45.258, + "args": { + "External id": 1407622,"Record function id": 0, "Sequence number": 15109051, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531394469.669, "dur": 1.304, + "args": { + "External id": 1407623,"Sequence number": 15109051, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 134 + } + }, + { + "ph": "f", "id": 16, "pid": 2338710, "tid": 2379450, "ts": 6410531394469.669, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531394474.484, "dur": 34.823, + "args": { + "External id": 1407624,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531394477.500, "dur": 31.334, + "args": { + "External id": 1407625,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531394486.689, "dur": 1.030, + "args": { + "External id": 1407626,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531394519.938, "dur": 3308.616, + "args": { + "External id": 1407627,"Record function id": 0, "Sequence number": 15109049, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531394523.980, "dur": 3263.795, + "args": { + "External id": 1407628,"Sequence number": 15109049, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 139 + } + }, + { + "ph": "f", "id": 17, "pid": 2338710, "tid": 2379450, "ts": 6410531394523.980, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531394567.777, "dur": 3.406, + "args": { + "External id": 1407629,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531394574.653, "dur": 2964.979, + "args": { + "External id": 1407630,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531394579.996, "dur": 2959.371, + "args": { + "External id": 1407631,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531394583.364, "dur": 5.281, + "args": { + "External id": 1407632,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531394589.659, "dur": 2948.237, + "args": { + "External id": 1407633,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338710, "tid": 2379450, + "ts": 6410531397543.590, "dur": 0.605, + "args": { + "External id": 1407634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397545.705, "dur": 3.175, + "args": { + "External id": 1407635,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397547.329, "dur": 1.413, + "args": { + "External id": 1407636,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2379450, + "ts": 6410531397554.002, "dur": 25.083, + "args": { + "External id": 1407637,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2379450, + "ts": 6410531397588.705, "dur": 46.369, + "args": { + "External id": 1407638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2379450, + "ts": 6410531397590.417, "dur": 44.427, + "args": { + "External id": 1407639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2379450, + "ts": 6410531397591.919, "dur": 42.550, + "args": { + "External id": 1407640,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397802.576, "dur": 18.908, + "args": { + "External id": 1407641,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531397841.435, "dur": 18.703, + "args": { + "External id": 1407642,"Record function id": 0, "Sequence number": 15109048, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531397846.127, "dur": 10.852, + "args": { + "External id": 1407643,"Sequence number": 15109048, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 154 + } + }, + { + "ph": "f", "id": 18, "pid": 2338710, "tid": 2379450, "ts": 6410531397846.127, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531397850.529, "dur": 6.211, + "args": { + "External id": 1407644,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531397852.024, "dur": 4.519, + "args": { + "External id": 1407645,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531397864.518, "dur": 91.106, + "args": { + "External id": 1407646,"Record function id": 0, "Sequence number": 15109047, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531397865.833, "dur": 83.170, + "args": { + "External id": 1407647,"Sequence number": 15109047, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 158 + } + }, + { + "ph": "f", "id": 19, "pid": 2338710, "tid": 2379450, "ts": 6410531397865.833, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531397870.476, "dur": 77.867, + "args": { + "External id": 1407648,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531397873.987, "dur": 25.369, + "args": { + "External id": 1407649,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531397875.941, "dur": 4.235, + "args": { + "External id": 1407650,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397881.175, "dur": 17.866, + "args": { + "External id": 1407651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397883.480, "dur": 15.051, + "args": { + "External id": 1407652,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531397901.393, "dur": 7.372, + "args": { + "External id": 1407653,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531397906.839, "dur": 1.523, + "args": { + "External id": 1407654,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397913.132, "dur": 34.257, + "args": { + "External id": 1407655,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531397960.756, "dur": 60.660, + "args": { + "External id": 1407656,"Record function id": 0, "Sequence number": 15109046, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531397961.855, "dur": 54.984, + "args": { + "External id": 1407657,"Sequence number": 15109046, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 168 + } + }, + { + "ph": "f", "id": 20, "pid": 2338710, "tid": 2379450, "ts": 6410531397961.855, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531397964.230, "dur": 52.278, + "args": { + "External id": 1407658,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531397966.553, "dur": 20.115, + "args": { + "External id": 1407659,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531397967.655, "dur": 3.436, + "args": { + "External id": 1407660,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397971.822, "dur": 14.570, + "args": { + "External id": 1407661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397972.851, "dur": 13.170, + "args": { + "External id": 1407662,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410531397988.115, "dur": 10.697, + "args": { + "External id": 1407663,"Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531397997.101, "dur": 1.077, + "args": { + "External id": 1407664,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531397999.655, "dur": 16.168, + "args": { + "External id": 1407665,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531398025.791, "dur": 173.983, + "args": { + "External id": 1407666,"Record function id": 0, "Sequence number": 15109045, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531398027.093, "dur": 165.562, + "args": { + "External id": 1407667,"Sequence number": 15109045, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 178 + } + }, + { + "ph": "f", "id": 21, "pid": 2338710, "tid": 2379450, "ts": 6410531398027.093, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531398029.152, "dur": 162.971, + "args": { + "External id": 1407668,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531398030.647, "dur": 19.875, + "args": { + "External id": 1407669,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531398031.483, "dur": 2.772, + "args": { + "External id": 1407670,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531398034.936, "dur": 15.272, + "args": { + "External id": 1407671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531398035.724, "dur": 14.001, + "args": { + "External id": 1407672,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531398051.711, "dur": 37.789, + "args": { + "External id": 1407673,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531398087.440, "dur": 1.345, + "args": { + "External id": 1407674,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531398093.010, "dur": 97.756, + "args": { + "External id": 1407675,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531398207.880, "dur": 120.786, + "args": { + "External id": 1407676,"Record function id": 0, "Sequence number": 15109044, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531398209.459, "dur": 97.141, + "args": { + "External id": 1407677,"Sequence number": 15109044, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 188 + } + }, + { + "ph": "f", "id": 22, "pid": 2338710, "tid": 2379450, "ts": 6410531398209.459, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531398213.869, "dur": 92.341, + "args": { + "External id": 1407678,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531398215.830, "dur": 22.607, + "args": { + "External id": 1407679,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531398216.896, "dur": 6.238, + "args": { + "External id": 1407680,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531398224.177, "dur": 13.940, + "args": { + "External id": 1407681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531398225.593, "dur": 12.106, + "args": { + "External id": 1407682,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531398239.898, "dur": 4.421, + "args": { + "External id": 1407683,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531398243.311, "dur": 0.781, + "args": { + "External id": 1407684,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531398247.882, "dur": 57.297, + "args": { + "External id": 1407685,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531398311.617, "dur": 15.438, + "args": { + "External id": 1407686,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531398336.983, "dur": 43.353, + "args": { + "External id": 1407687,"Record function id": 0, "Sequence number": 15109043, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531398338.919, "dur": 1.507, + "args": { + "External id": 1407688,"Sequence number": 15109043, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 199 + } + }, + { + "ph": "f", "id": 23, "pid": 2338710, "tid": 2379450, "ts": 6410531398338.919, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531398343.182, "dur": 29.375, + "args": { + "External id": 1407689,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531398345.757, "dur": 26.300, + "args": { + "External id": 1407690,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531398351.614, "dur": 0.847, + "args": { + "External id": 1407691,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531398385.891, "dur": 3420.016, + "args": { + "External id": 1407692,"Record function id": 0, "Sequence number": 15109042, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531398401.189, "dur": 3363.204, + "args": { + "External id": 1407693,"Sequence number": 15109042, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 204 + } + }, + { + "ph": "f", "id": 24, "pid": 2338710, "tid": 2379450, "ts": 6410531398401.189, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531398452.445, "dur": 3.140, + "args": { + "External id": 1407694,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531398458.915, "dur": 3066.667, + "args": { + "External id": 1407695,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531398463.410, "dur": 3061.861, + "args": { + "External id": 1407696,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531398468.901, "dur": 4.949, + "args": { + "External id": 1407697,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531398474.961, "dur": 3049.146, + "args": { + "External id": 1407698,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338710, "tid": 2379450, + "ts": 6410531401529.796, "dur": 0.459, + "args": { + "External id": 1407699,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410531401531.666, "dur": 2.845, + "args": { + "External id": 1407700,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410531401533.356, "dur": 1.010, + "args": { + "External id": 1407701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2379450, + "ts": 6410531401539.455, "dur": 24.435, + "args": { + "External id": 1407702,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2379450, + "ts": 6410531401569.365, "dur": 47.305, + "args": { + "External id": 1407703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2379450, + "ts": 6410531401570.726, "dur": 45.704, + "args": { + "External id": 1407704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2379450, + "ts": 6410531401572.242, "dur": 43.821, + "args": { + "External id": 1407705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531401780.324, "dur": 19.078, + "args": { + "External id": 1407706,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531401822.976, "dur": 18.674, + "args": { + "External id": 1407707,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531401826.275, "dur": 13.701, + "args": { + "External id": 1407708,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531401830.317, "dur": 8.372, + "args": { + "External id": 1407709,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531401834.358, "dur": 4.167, + "args": { + "External id": 1407710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531401846.324, "dur": 16.667, + "args": { + "External id": 1407711,"Record function id": 0, "Sequence number": 15109041, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531401847.844, "dur": 11.808, + "args": { + "External id": 1407712,"Sequence number": 15109041, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 223 + } + }, + { + "ph": "f", "id": 25, "pid": 2338710, "tid": 2379450, "ts": 6410531401847.844, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531401851.830, "dur": 7.585, + "args": { + "External id": 1407713,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531401855.537, "dur": 3.701, + "args": { + "External id": 1407714,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531401867.305, "dur": 91.830, + "args": { + "External id": 1407715,"Record function id": 0, "Sequence number": 15109040, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531401868.841, "dur": 83.486, + "args": { + "External id": 1407716,"Sequence number": 15109040, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 227 + } + }, + { + "ph": "f", "id": 26, "pid": 2338710, "tid": 2379450, "ts": 6410531401868.841, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531401871.445, "dur": 80.451, + "args": { + "External id": 1407717,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531401874.256, "dur": 32.051, + "args": { + "External id": 1407718,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531401876.204, "dur": 6.552, + "args": { + "External id": 1407719,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531401884.107, "dur": 21.881, + "args": { + "External id": 1407720,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531401886.476, "dur": 18.917, + "args": { + "External id": 1407721,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531401910.430, "dur": 7.529, + "args": { + "External id": 1407722,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531401916.009, "dur": 1.565, + "args": { + "External id": 1407723,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531401919.273, "dur": 31.691, + "args": { + "External id": 1407724,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531401964.428, "dur": 61.428, + "args": { + "External id": 1407725,"Record function id": 0, "Sequence number": 15109039, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531401965.697, "dur": 55.917, + "args": { + "External id": 1407726,"Sequence number": 15109039, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 237 + } + }, + { + "ph": "f", "id": 27, "pid": 2338710, "tid": 2379450, "ts": 6410531401965.697, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531401967.961, "dur": 53.275, + "args": { + "External id": 1407727,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531401970.016, "dur": 23.960, + "args": { + "External id": 1407728,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531401975.016, "dur": 2.948, + "args": { + "External id": 1407729,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531401978.972, "dur": 14.655, + "args": { + "External id": 1407730,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531401980.162, "dur": 13.077, + "args": { + "External id": 1407731,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410531401998.324, "dur": 5.424, + "args": { + "External id": 1407732,"Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531402002.201, "dur": 0.840, + "args": { + "External id": 1407733,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531402004.590, "dur": 16.059, + "args": { + "External id": 1407734,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402030.354, "dur": 176.306, + "args": { + "External id": 1407735,"Record function id": 0, "Sequence number": 15109038, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402031.834, "dur": 168.117, + "args": { + "External id": 1407736,"Sequence number": 15109038, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 247 + } + }, + { + "ph": "f", "id": 28, "pid": 2338710, "tid": 2379450, "ts": 6410531402031.834, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531402033.909, "dur": 165.427, + "args": { + "External id": 1407737,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531402037.893, "dur": 52.970, + "args": { + "External id": 1407738,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531402039.223, "dur": 2.354, + "args": { + "External id": 1407739,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531402042.211, "dur": 48.338, + "args": { + "External id": 1407740,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531402043.563, "dur": 46.181, + "args": { + "External id": 1407741,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531402096.226, "dur": 3.403, + "args": { + "External id": 1407742,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531402098.279, "dur": 1.017, + "args": { + "External id": 1407743,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531402100.536, "dur": 97.657, + "args": { + "External id": 1407744,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402214.311, "dur": 153.393, + "args": { + "External id": 1407745,"Record function id": 0, "Sequence number": 15109037, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402216.199, "dur": 125.225, + "args": { + "External id": 1407746,"Sequence number": 15109037, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 257 + } + }, + { + "ph": "f", "id": 29, "pid": 2338710, "tid": 2379450, "ts": 6410531402216.199, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531402218.629, "dur": 122.297, + "args": { + "External id": 1407747,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410531402220.499, "dur": 34.062, + "args": { + "External id": 1407748,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531402226.312, "dur": 3.205, + "args": { + "External id": 1407749,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410531402234.502, "dur": 19.734, + "args": { + "External id": 1407750,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410531402238.987, "dur": 14.817, + "args": { + "External id": 1407751,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531402258.509, "dur": 2.657, + "args": { + "External id": 1407752,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531402260.069, "dur": 0.844, + "args": { + "External id": 1407753,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531402262.061, "dur": 77.863, + "args": { + "External id": 1407754,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531402346.704, "dur": 18.334, + "args": { + "External id": 1407755,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531402375.241, "dur": 429.624, + "args": { + "External id": 1407756,"Record function id": 0, "Sequence number": 15109036, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531402377.111, "dur": 415.246, + "args": { + "External id": 1407757,"Sequence number": 15109036, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 268 + } + }, + { + "ph": "f", "id": 30, "pid": 2338710, "tid": 2379450, "ts": 6410531402377.111, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402599.138, "dur": 53.067, + "args": { + "External id": 1407758,"kernel_hash": "c2hiad6vohc5juoazzm5elv5p6zjifqe63zwhygqq3luayunx4no", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "131072", "4096", "1", "993", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/2h/c2hiad6vohc5juoazzm5elv5p6zjifqe63zwhygqq3luayunx4no.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[131072, 4096], [4096], [131072, 4096], [131072, 4096], [132, 4096], [131072], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402694.956, "dur": 29.095, + "args": { + "External id": 1407759,"kernel_hash": "c6346guyxknvaslrs2ei3ec2tw4wgztd2bkmy2hswhmzwewgk7bb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/63/c6346guyxknvaslrs2ei3ec2tw4wgztd2bkmy2hswhmzwewgk7bb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531402744.072, "dur": 22.004, + "args": { + "External id": 1407760,"kernel_hash": "cey5irmf4ovxj63ncyq4qfgp27xz4mzqhlhvmoqbijvnsrskn4ba", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/ey/cey5irmf4ovxj63ncyq4qfgp27xz4mzqhlhvmoqbijvnsrskn4ba.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531402817.345, "dur": 15.288, + "args": { + "External id": 1407761,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531402819.835, "dur": 11.760, + "args": { + "External id": 1407762,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531402823.436, "dur": 7.211, + "args": { + "External id": 1407763,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531402826.799, "dur": 3.682, + "args": { + "External id": 1407764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: StackBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402836.934, "dur": 50.472, + "args": { + "External id": 1407765,"Record function id": 0, "Sequence number": 15109035, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402838.038, "dur": 36.461, + "args": { + "External id": 1407766,"Sequence number": 15109035, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 277 + } + }, + { + "ph": "f", "id": 31, "pid": 2338710, "tid": 2379450, "ts": 6410531402838.038, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410531402840.885, "dur": 11.217, + "args": { + "External id": 1407767,"Record function id": 0, "Concrete Inputs": ["", "-2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531402847.902, "dur": 1.724, + "args": { + "External id": 1407768,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410531402852.964, "dur": 8.684, + "args": { + "External id": 1407769,"Record function id": 0, "Concrete Inputs": ["", "-2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531402859.956, "dur": 0.845, + "args": { + "External id": 1407770,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410531402862.334, "dur": 4.754, + "args": { + "External id": 1407771,"Record function id": 0, "Concrete Inputs": ["", "-2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531402863.598, "dur": 2.900, + "args": { + "External id": 1407772,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410531402868.137, "dur": 5.543, + "args": { + "External id": 1407773,"Record function id": 0, "Concrete Inputs": ["", "-2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531402872.098, "dur": 0.874, + "args": { + "External id": 1407774,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402891.880, "dur": 6.546, + "args": { + "External id": 1407775,"Record function id": 0, "Sequence number": 15109034, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531402893.288, "dur": 1.596, + "args": { + "External id": 1407776,"Sequence number": 15109034, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 287 + } + }, + { + "ph": "f", "id": 32, "pid": 2338710, "tid": 2379450, "ts": 6410531402893.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531402903.761, "dur": 744.225, + "args": { + "External id": 1407777,"Record function id": 0, "Sequence number": 15109033, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531402905.184, "dur": 720.678, + "args": { + "External id": 1407778,"Sequence number": 15109033, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 289 + } + }, + { + "ph": "f", "id": 33, "pid": 2338710, "tid": 2379450, "ts": 6410531402905.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531402959.161, "dur": 14.401, + "args": { + "External id": 1407779,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531402968.544, "dur": 4.638, + "args": { + "External id": 1407780,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531402980.762, "dur": 7.847, + "args": { + "External id": 1407781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531402984.862, "dur": 2.918, + "args": { + "External id": 1407782,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531402986.432, "dur": 1.074, + "args": { + "External id": 1407783,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2379450, + "ts": 6410531402996.523, "dur": 207.668, + "args": { + "External id": 1407784,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531402997.742, "dur": 6.050, + "args": { + "External id": 1407785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531402998.589, "dur": 4.272, + "args": { + "External id": 1407786,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403002.059, "dur": 0.689, + "args": { + "External id": 1407787,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2379450, + "ts": 6410531403006.299, "dur": 196.838, + "args": { + "External id": 1407788,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531403009.822, "dur": 190.774, + "args": { + "External id": 1407789,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531403215.049, "dur": 9.716, + "args": { + "External id": 1407790,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531403220.482, "dur": 4.100, + "args": { + "External id": 1407791,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531403275.746, "dur": 6.996, + "args": { + "External id": 1407792,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531403284.388, "dur": 5.361, + "args": { + "External id": 1407793,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531403293.104, "dur": 3.190, + "args": { + "External id": 1407794,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531403343.130, "dur": 3.043, + "args": { + "External id": 1407795,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531403344.423, "dur": 1.563, + "args": { + "External id": 1407796,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338710, "tid": 2379450, + "ts": 6410531403382.862, "dur": 210.414, + "args": { + "External id": 1407797,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410531403392.280, "dur": 12.607, + "args": { + "External id": 1407798,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403399.841, "dur": 1.295, + "args": { + "External id": 1407799,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531403407.563, "dur": 25.873, + "args": { + "External id": 1407800,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403414.154, "dur": 17.449, + "args": { + "External id": 1407801,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410531403436.646, "dur": 5.494, + "args": { + "External id": 1407802,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403441.045, "dur": 0.659, + "args": { + "External id": 1407803,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531403442.747, "dur": 4.860, + "args": { + "External id": 1407804,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403446.187, "dur": 0.788, + "args": { + "External id": 1407805,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531403452.687, "dur": 5.267, + "args": { + "External id": 1407806,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403457.047, "dur": 0.562, + "args": { + "External id": 1407807,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531403461.147, "dur": 11.904, + "args": { + "External id": 1407808,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531403467.727, "dur": 5.093, + "args": { + "External id": 1407809,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531403474.369, "dur": 4.706, + "args": { + "External id": 1407810,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403478.242, "dur": 0.500, + "args": { + "External id": 1407811,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531403479.960, "dur": 2.792, + "args": { + "External id": 1407812,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531403480.993, "dur": 1.591, + "args": { + "External id": 1407813,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531403485.793, "dur": 92.107, + "args": { + "External id": 1407814,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531403580.302, "dur": 1.229, + "args": { + "External id": 1407815,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531403585.152, "dur": 2.929, + "args": { + "External id": 1407816,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403586.542, "dur": 0.616, + "args": { + "External id": 1407817,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531403590.540, "dur": 1.167, + "args": { + "External id": 1407818,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531403664.427, "dur": 12.306, + "args": { + "External id": 1407819,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531403667.390, "dur": 8.350, + "args": { + "External id": 1407820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531403670.609, "dur": 4.096, + "args": { + "External id": 1407821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531403671.707, "dur": 2.869, + "args": { + "External id": 1407822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403681.747, "dur": 12.363, + "args": { + "External id": 1407823,"Record function id": 0, "Sequence number": 15109032, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403682.991, "dur": 7.776, + "args": { + "External id": 1407824,"Sequence number": 15109032, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 335 + } + }, + { + "ph": "f", "id": 34, "pid": 2338710, "tid": 2379450, "ts": 6410531403682.991, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531403687.960, "dur": 2.564, + "args": { + "External id": 1407825,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531403688.921, "dur": 1.488, + "args": { + "External id": 1407826,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403698.882, "dur": 164.063, + "args": { + "External id": 1407827,"Record function id": 0, "Sequence number": 15109031, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403700.167, "dur": 152.530, + "args": { + "External id": 1407828,"Sequence number": 15109031, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 339 + } + }, + { + "ph": "f", "id": 35, "pid": 2338710, "tid": 2379450, "ts": 6410531403700.167, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531403709.645, "dur": 5.297, + "args": { + "External id": 1407829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531403711.746, "dur": 2.418, + "args": { + "External id": 1407830,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403713.241, "dur": 0.702, + "args": { + "External id": 1407831,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531403716.535, "dur": 60.083, + "args": { + "External id": 1407832,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531403778.396, "dur": 9.865, + "args": { + "External id": 1407833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531403779.427, "dur": 7.980, + "args": { + "External id": 1407834,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403783.647, "dur": 3.541, + "args": { + "External id": 1407835,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531403790.231, "dur": 6.380, + "args": { + "External id": 1407836,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531403791.878, "dur": 4.176, + "args": { + "External id": 1407837,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403795.424, "dur": 0.527, + "args": { + "External id": 1407838,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531403797.597, "dur": 54.071, + "args": { + "External id": 1407839,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403868.607, "dur": 8.671, + "args": { + "External id": 1407840,"Record function id": 0, "Sequence number": 15109030, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403869.925, "dur": 5.092, + "args": { + "External id": 1407841,"Sequence number": 15109030, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 352 + } + }, + { + "ph": "f", "id": 36, "pid": 2338710, "tid": 2379450, "ts": 6410531403869.925, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531403871.913, "dur": 2.901, + "args": { + "External id": 1407842,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531403872.719, "dur": 1.966, + "args": { + "External id": 1407843,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403881.822, "dur": 17.611, + "args": { + "External id": 1407844,"Record function id": 0, "Sequence number": 15109029, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403886.130, "dur": 9.014, + "args": { + "External id": 1407845,"Sequence number": 15109029, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 356 + } + }, + { + "ph": "f", "id": 37, "pid": 2338710, "tid": 2379450, "ts": 6410531403886.130, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531403887.643, "dur": 7.254, + "args": { + "External id": 1407846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531403888.696, "dur": 5.649, + "args": { + "External id": 1407847,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403893.430, "dur": 0.750, + "args": { + "External id": 1407848,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531403903.902, "dur": 6.425, + "args": { + "External id": 1407849,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531403905.442, "dur": 4.329, + "args": { + "External id": 1407850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531403906.712, "dur": 2.640, + "args": { + "External id": 1407851,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531403907.508, "dur": 1.740, + "args": { + "External id": 1407852,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403916.752, "dur": 10.882, + "args": { + "External id": 1407853,"Record function id": 0, "Sequence number": 15109028, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403917.744, "dur": 6.775, + "args": { + "External id": 1407854,"Sequence number": 15109028, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 365 + } + }, + { + "ph": "f", "id": 38, "pid": 2338710, "tid": 2379450, "ts": 6410531403917.744, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531403919.247, "dur": 5.111, + "args": { + "External id": 1407855,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531403922.868, "dur": 1.367, + "args": { + "External id": 1407856,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403931.375, "dur": 177.066, + "args": { + "External id": 1407857,"Record function id": 0, "Sequence number": 15109027, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531403932.533, "dur": 109.154, + "args": { + "External id": 1407858,"Sequence number": 15109027, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 369 + } + }, + { + "ph": "f", "id": 39, "pid": 2338710, "tid": 2379450, "ts": 6410531403932.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531403936.134, "dur": 3.470, + "args": { + "External id": 1407859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531403937.127, "dur": 1.949, + "args": { + "External id": 1407860,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403938.408, "dur": 0.491, + "args": { + "External id": 1407861,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531403942.659, "dur": 43.452, + "args": { + "External id": 1407862,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531403987.767, "dur": 7.026, + "args": { + "External id": 1407863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531403988.664, "dur": 5.505, + "args": { + "External id": 1407864,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531403992.681, "dur": 1.341, + "args": { + "External id": 1407865,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531403995.963, "dur": 6.897, + "args": { + "External id": 1407866,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531403997.247, "dur": 4.934, + "args": { + "External id": 1407867,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531404001.218, "dur": 0.888, + "args": { + "External id": 1407868,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531404003.809, "dur": 37.087, + "args": { + "External id": 1407869,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531404118.156, "dur": 53.045, + "args": { + "External id": 1407870,"Record function id": 0, "Sequence number": 15109026, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531404120.098, "dur": 9.732, + "args": { + "External id": 1407871,"Sequence number": 15109026, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 382 + } + }, + { + "ph": "f", "id": 40, "pid": 2338710, "tid": 2379450, "ts": 6410531404120.098, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531404123.233, "dur": 6.412, + "args": { + "External id": 1407872,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531404127.001, "dur": 2.463, + "args": { + "External id": 1407873,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531404134.925, "dur": 32.523, + "args": { + "External id": 1407874,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531404176.177, "dur": 12.892, + "args": { + "External id": 1407875,"Record function id": 0, "Sequence number": 15109025, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531404177.528, "dur": 8.608, + "args": { + "External id": 1407876,"Sequence number": 15109025, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 387 + } + }, + { + "ph": "f", "id": 41, "pid": 2338710, "tid": 2379450, "ts": 6410531404177.528, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531404180.980, "dur": 4.848, + "args": { + "External id": 1407877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531404182.290, "dur": 2.886, + "args": { + "External id": 1407878,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531404184.276, "dur": 0.765, + "args": { + "External id": 1407879,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531404194.056, "dur": 7.518, + "args": { + "External id": 1407880,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531404195.677, "dur": 5.311, + "args": { + "External id": 1407881,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531404197.484, "dur": 2.972, + "args": { + "External id": 1407882,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531404198.547, "dur": 1.821, + "args": { + "External id": 1407883,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531404206.948, "dur": 572.490, + "args": { + "External id": 1407884,"Record function id": 0, "Sequence number": 15109024, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531404208.495, "dur": 551.037, + "args": { + "External id": 1407885,"Sequence number": 15109024, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 396 + } + }, + { + "ph": "f", "id": 42, "pid": 2338710, "tid": 2379450, "ts": 6410531404208.495, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2379450, + "ts": 6410531404245.115, "dur": 44.912, + "args": { + "External id": 1407886,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531404247.467, "dur": 42.284, + "args": { + "External id": 1407887,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531404251.325, "dur": 8.098, + "args": { + "External id": 1407888,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531404254.675, "dur": 4.037, + "args": { + "External id": 1407889,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531404261.069, "dur": 28.089, + "args": { + "External id": 1407890,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531404307.984, "dur": 5.380, + "args": { + "External id": 1407891,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531404308.892, "dur": 4.355, + "args": { + "External id": 1407892,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531404318.701, "dur": 1.895, + "args": { + "External id": 1407893,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531404319.401, "dur": 1.067, + "args": { + "External id": 1407894,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531404343.343, "dur": 3.239, + "args": { + "External id": 1407895,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531404361.309, "dur": 3.145, + "args": { + "External id": 1407896,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531404612.142, "dur": 4.694, + "args": { + "External id": 1407897,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531404622.966, "dur": 45.421, + "args": { + "External id": 1407898,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531404638.366, "dur": 1.303, + "args": { + "External id": 1407899,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531404676.006, "dur": 40.703, + "args": { + "External id": 1407900,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531404678.599, "dur": 37.770, + "args": { + "External id": 1407901,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531404683.402, "dur": 6.534, + "args": { + "External id": 1407902,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531404694.591, "dur": 21.282, + "args": { + "External id": 1407903,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531404722.370, "dur": 3.062, + "args": { + "External id": 1407904,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531404723.812, "dur": 1.464, + "args": { + "External id": 1407905,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531404733.730, "dur": 8.637, + "args": { + "External id": 1407906,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531404737.403, "dur": 4.828, + "args": { + "External id": 1407907,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531404744.838, "dur": 2.299, + "args": { + "External id": 1407908,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531404746.151, "dur": 0.875, + "args": { + "External id": 1407909,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531404794.395, "dur": 10.881, + "args": { + "External id": 1407910,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531404796.947, "dur": 7.396, + "args": { + "External id": 1407911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531404799.609, "dur": 3.498, + "args": { + "External id": 1407912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531404800.756, "dur": 2.240, + "args": { + "External id": 1407913,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531404809.598, "dur": 13.216, + "args": { + "External id": 1407914,"Record function id": 0, "Sequence number": 15109023, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531404811.257, "dur": 7.319, + "args": { + "External id": 1407915,"Sequence number": 15109023, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 426 + } + }, + { + "ph": "f", "id": 43, "pid": 2338710, "tid": 2379450, "ts": 6410531404811.257, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531404816.026, "dur": 2.315, + "args": { + "External id": 1407916,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531404816.889, "dur": 1.320, + "args": { + "External id": 1407917,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531404829.711, "dur": 174.855, + "args": { + "External id": 1407918,"Record function id": 0, "Sequence number": 15109022, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531404830.969, "dur": 167.099, + "args": { + "External id": 1407919,"Sequence number": 15109022, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 430 + } + }, + { + "ph": "f", "id": 44, "pid": 2338710, "tid": 2379450, "ts": 6410531404830.969, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531404836.293, "dur": 5.530, + "args": { + "External id": 1407920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531404837.887, "dur": 3.127, + "args": { + "External id": 1407921,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531404839.467, "dur": 1.349, + "args": { + "External id": 1407922,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531404843.201, "dur": 86.032, + "args": { + "External id": 1407923,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531404930.842, "dur": 10.170, + "args": { + "External id": 1407924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531404932.187, "dur": 8.019, + "args": { + "External id": 1407925,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531404935.816, "dur": 4.148, + "args": { + "External id": 1407926,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531404943.081, "dur": 6.903, + "args": { + "External id": 1407927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531404944.162, "dur": 5.146, + "args": { + "External id": 1407928,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531404948.428, "dur": 0.802, + "args": { + "External id": 1407929,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531404950.463, "dur": 46.571, + "args": { + "External id": 1407930,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531405010.422, "dur": 14.085, + "args": { + "External id": 1407931,"Record function id": 0, "Sequence number": 15109021, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531405011.495, "dur": 9.642, + "args": { + "External id": 1407932,"Sequence number": 15109021, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 443 + } + }, + { + "ph": "f", "id": 45, "pid": 2338710, "tid": 2379450, "ts": 6410531405011.495, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531405013.957, "dur": 6.979, + "args": { + "External id": 1407933,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531405017.147, "dur": 3.645, + "args": { + "External id": 1407934,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531405029.135, "dur": 11.091, + "args": { + "External id": 1407935,"Record function id": 0, "Sequence number": 15109020, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531405030.218, "dur": 7.652, + "args": { + "External id": 1407936,"Sequence number": 15109020, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 447 + } + }, + { + "ph": "f", "id": 46, "pid": 2338710, "tid": 2379450, "ts": 6410531405030.218, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531405031.255, "dur": 6.356, + "args": { + "External id": 1407937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531405031.987, "dur": 5.042, + "args": { + "External id": 1407938,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405036.374, "dur": 0.529, + "args": { + "External id": 1407939,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531405044.800, "dur": 5.624, + "args": { + "External id": 1407940,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531405046.076, "dur": 3.767, + "args": { + "External id": 1407941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531405047.120, "dur": 2.372, + "args": { + "External id": 1407942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531405048.173, "dur": 1.196, + "args": { + "External id": 1407943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531405110.204, "dur": 14.339, + "args": { + "External id": 1407944,"Record function id": 0, "Sequence number": 15109019, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531405115.147, "dur": 6.072, + "args": { + "External id": 1407945,"Sequence number": 15109019, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 456 + } + }, + { + "ph": "f", "id": 47, "pid": 2338710, "tid": 2379450, "ts": 6410531405115.147, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531405117.167, "dur": 3.846, + "args": { + "External id": 1407946,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531405118.195, "dur": 2.546, + "args": { + "External id": 1407947,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531405133.373, "dur": 499.344, + "args": { + "External id": 1407948,"Record function id": 0, "Sequence number": 15109018, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531405134.927, "dur": 471.764, + "args": { + "External id": 1407949,"Sequence number": 15109018, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 460 + } + }, + { + "ph": "f", "id": 48, "pid": 2338710, "tid": 2379450, "ts": 6410531405134.927, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531405160.818, "dur": 14.339, + "args": { + "External id": 1407950,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405168.834, "dur": 5.727, + "args": { + "External id": 1407951,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531405177.819, "dur": 4.662, + "args": { + "External id": 1407952,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405179.108, "dur": 3.136, + "args": { + "External id": 1407953,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531405184.177, "dur": 6.353, + "args": { + "External id": 1407954,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405187.783, "dur": 2.520, + "args": { + "External id": 1407955,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531405230.186, "dur": 344.532, + "args": { + "External id": 1407956,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531405342.019, "dur": 3.977, + "args": { + "External id": 1407957,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531405350.490, "dur": 6.680, + "args": { + "External id": 1407958,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531405361.109, "dur": 2.064, + "args": { + "External id": 1407959,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531405364.197, "dur": 2.300, + "args": { + "External id": 1407960,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531405441.876, "dur": 3.780, + "args": { + "External id": 1407961,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531405442.912, "dur": 2.317, + "args": { + "External id": 1407962,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531405448.127, "dur": 36.164, + "args": { + "External id": 1407963,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405453.863, "dur": 3.207, + "args": { + "External id": 1407964,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531405485.909, "dur": 1.586, + "args": { + "External id": 1407965,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531405486.841, "dur": 0.584, + "args": { + "External id": 1407966,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531405494.576, "dur": 21.466, + "args": { + "External id": 1407967,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405499.553, "dur": 0.691, + "args": { + "External id": 1407968,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531405591.198, "dur": 4.772, + "args": { + "External id": 1407969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531405599.517, "dur": 0.880, + "args": { + "External id": 1407970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531405602.932, "dur": 0.715, + "args": { + "External id": 1407971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531405645.658, "dur": 296.237, + "args": { + "External id": 1407972,"Record function id": 0, "Sequence number": 15109017, "Fwd thread id": 1, "Ev Idx": 483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531405647.721, "dur": 285.368, + "args": { + "External id": 1407973,"Sequence number": 15109017, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 484 + } + }, + { + "ph": "f", "id": 49, "pid": 2338710, "tid": 2379450, "ts": 6410531405647.721, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531405676.512, "dur": 56.259, + "args": { + "External id": 1407974,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405680.289, "dur": 4.752, + "args": { + "External id": 1407975,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531405687.241, "dur": 44.826, + "args": { + "External id": 1407976,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531405746.204, "dur": 7.051, + "args": { + "External id": 1407977,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405750.480, "dur": 2.412, + "args": { + "External id": 1407978,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531405950.943, "dur": 282.117, + "args": { + "External id": 1407979,"Record function id": 0, "Sequence number": 15109016, "Fwd thread id": 1, "Ev Idx": 490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531405952.988, "dur": 268.399, + "args": { + "External id": 1407980,"Sequence number": 15109016, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 491 + } + }, + { + "ph": "f", "id": 50, "pid": 2338710, "tid": 2379450, "ts": 6410531405952.988, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531405967.736, "dur": 57.782, + "args": { + "External id": 1407981,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531405970.287, "dur": 5.456, + "args": { + "External id": 1407982,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531405977.145, "dur": 47.639, + "args": { + "External id": 1407983,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531406033.766, "dur": 10.248, + "args": { + "External id": 1407984,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406040.192, "dur": 3.501, + "args": { + "External id": 1407985,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406244.438, "dur": 19.407, + "args": { + "External id": 1407986,"Record function id": 0, "Sequence number": 15109015, "Fwd thread id": 1, "Ev Idx": 497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406248.969, "dur": 11.103, + "args": { + "External id": 1407987,"Sequence number": 15109015, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 498 + } + }, + { + "ph": "f", "id": 51, "pid": 2338710, "tid": 2379450, "ts": 6410531406248.969, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406252.847, "dur": 6.890, + "args": { + "External id": 1407988,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406254.099, "dur": 5.427, + "args": { + "External id": 1407989,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406267.967, "dur": 9.261, + "args": { + "External id": 1407990,"Record function id": 0, "Sequence number": 15109014, "Fwd thread id": 1, "Ev Idx": 501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406269.174, "dur": 6.277, + "args": { + "External id": 1407991,"Sequence number": 15109014, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 502 + } + }, + { + "ph": "f", "id": 52, "pid": 2338710, "tid": 2379450, "ts": 6410531406269.174, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406270.566, "dur": 4.726, + "args": { + "External id": 1407992,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406273.839, "dur": 1.337, + "args": { + "External id": 1407993,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406280.975, "dur": 11.130, + "args": { + "External id": 1407994,"Record function id": 0, "Sequence number": 15109013, "Fwd thread id": 1, "Ev Idx": 505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406282.431, "dur": 6.614, + "args": { + "External id": 1407995,"Sequence number": 15109013, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 506 + } + }, + { + "ph": "f", "id": 53, "pid": 2338710, "tid": 2379450, "ts": 6410531406282.431, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406283.685, "dur": 5.189, + "args": { + "External id": 1407996,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406287.785, "dur": 0.977, + "args": { + "External id": 1407997,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406296.027, "dur": 38.424, + "args": { + "External id": 1407998,"Record function id": 0, "Sequence number": 15109012, "Fwd thread id": 1, "Ev Idx": 509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406297.104, "dur": 34.255, + "args": { + "External id": 1407999,"Sequence number": 15109012, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 510 + } + }, + { + "ph": "f", "id": 54, "pid": 2338710, "tid": 2379450, "ts": 6410531406297.104, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406300.459, "dur": 30.724, + "args": { + "External id": 1408000,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406329.014, "dur": 1.988, + "args": { + "External id": 1408001,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406338.564, "dur": 223.414, + "args": { + "External id": 1408002,"Record function id": 0, "Sequence number": 15109011, "Fwd thread id": 1, "Ev Idx": 513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406339.402, "dur": 210.955, + "args": { + "External id": 1408003,"Sequence number": 15109011, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 514 + } + }, + { + "ph": "f", "id": 55, "pid": 2338710, "tid": 2379450, "ts": 6410531406339.402, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406348.095, "dur": 7.042, + "args": { + "External id": 1408004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406350.446, "dur": 3.967, + "args": { + "External id": 1408005,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406352.253, "dur": 1.876, + "args": { + "External id": 1408006,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531406357.397, "dur": 105.865, + "args": { + "External id": 1408007,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406466.654, "dur": 13.382, + "args": { + "External id": 1408008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406467.977, "dur": 10.705, + "args": { + "External id": 1408009,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406472.196, "dur": 6.254, + "args": { + "External id": 1408010,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406482.895, "dur": 6.140, + "args": { + "External id": 1408011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406484.425, "dur": 4.028, + "args": { + "External id": 1408012,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406487.872, "dur": 0.454, + "args": { + "External id": 1408013,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531406489.733, "dur": 59.309, + "args": { + "External id": 1408014,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406570.553, "dur": 10.993, + "args": { + "External id": 1408015,"Record function id": 0, "Sequence number": 15109010, "Fwd thread id": 1, "Ev Idx": 526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406571.713, "dur": 7.279, + "args": { + "External id": 1408016,"Sequence number": 15109010, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 527 + } + }, + { + "ph": "f", "id": 56, "pid": 2338710, "tid": 2379450, "ts": 6410531406571.713, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406573.332, "dur": 5.461, + "args": { + "External id": 1408017,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406576.813, "dur": 1.858, + "args": { + "External id": 1408018,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406585.639, "dur": 12.329, + "args": { + "External id": 1408019,"Record function id": 0, "Sequence number": 15109009, "Fwd thread id": 1, "Ev Idx": 530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406586.733, "dur": 7.713, + "args": { + "External id": 1408020,"Sequence number": 15109009, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 531 + } + }, + { + "ph": "f", "id": 57, "pid": 2338710, "tid": 2379450, "ts": 6410531406586.733, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406587.901, "dur": 6.277, + "args": { + "External id": 1408021,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406588.771, "dur": 4.767, + "args": { + "External id": 1408022,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406592.582, "dur": 0.849, + "args": { + "External id": 1408023,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531406604.886, "dur": 13.308, + "args": { + "External id": 1408024,"Record function id": 0, "Ev Idx": 535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531406606.500, "dur": 10.649, + "args": { + "External id": 1408025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531406609.526, "dur": 7.135, + "args": { + "External id": 1408026,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531406613.321, "dur": 3.146, + "args": { + "External id": 1408027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406624.856, "dur": 6.810, + "args": { + "External id": 1408028,"Record function id": 0, "Sequence number": 15109008, "Fwd thread id": 1, "Ev Idx": 539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406625.725, "dur": 2.770, + "args": { + "External id": 1408029,"Sequence number": 15109008, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 540 + } + }, + { + "ph": "f", "id": 58, "pid": 2338710, "tid": 2379450, "ts": 6410531406625.725, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406626.839, "dur": 1.462, + "args": { + "External id": 1408030,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406627.394, "dur": 0.777, + "args": { + "External id": 1408031,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406635.627, "dur": 116.768, + "args": { + "External id": 1408032,"Record function id": 0, "Sequence number": 15109007, "Fwd thread id": 1, "Ev Idx": 543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406636.428, "dur": 106.346, + "args": { + "External id": 1408033,"Sequence number": 15109007, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 544 + } + }, + { + "ph": "f", "id": 59, "pid": 2338710, "tid": 2379450, "ts": 6410531406636.428, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406641.157, "dur": 4.952, + "args": { + "External id": 1408034,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406641.919, "dur": 3.688, + "args": { + "External id": 1408035,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406644.986, "dur": 0.473, + "args": { + "External id": 1408036,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531406646.811, "dur": 36.215, + "args": { + "External id": 1408037,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406684.417, "dur": 6.661, + "args": { + "External id": 1408038,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406685.281, "dur": 5.146, + "args": { + "External id": 1408039,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406689.159, "dur": 1.126, + "args": { + "External id": 1408040,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406692.731, "dur": 6.242, + "args": { + "External id": 1408041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406697.319, "dur": 1.142, + "args": { + "External id": 1408042,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406697.935, "dur": 0.450, + "args": { + "External id": 1408043,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531406699.494, "dur": 42.441, + "args": { + "External id": 1408044,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406758.183, "dur": 43.214, + "args": { + "External id": 1408045,"Record function id": 0, "Sequence number": 15109006, "Fwd thread id": 1, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406759.363, "dur": 6.664, + "args": { + "External id": 1408046,"Sequence number": 15109006, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 557 + } + }, + { + "ph": "f", "id": 60, "pid": 2338710, "tid": 2379450, "ts": 6410531406759.363, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406760.963, "dur": 4.906, + "args": { + "External id": 1408047,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406764.517, "dur": 1.197, + "args": { + "External id": 1408048,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531406769.904, "dur": 28.516, + "args": { + "External id": 1408049,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406806.277, "dur": 10.594, + "args": { + "External id": 1408050,"Record function id": 0, "Sequence number": 15109005, "Fwd thread id": 1, "Ev Idx": 561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406809.810, "dur": 5.050, + "args": { + "External id": 1408051,"Sequence number": 15109005, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 562 + } + }, + { + "ph": "f", "id": 61, "pid": 2338710, "tid": 2379450, "ts": 6410531406809.810, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406810.833, "dur": 3.770, + "args": { + "External id": 1408052,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406811.869, "dur": 2.161, + "args": { + "External id": 1408053,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406813.248, "dur": 0.640, + "args": { + "External id": 1408054,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531406821.546, "dur": 8.444, + "args": { + "External id": 1408055,"Record function id": 0, "Ev Idx": 566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531406822.842, "dur": 6.477, + "args": { + "External id": 1408056,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531406823.942, "dur": 4.831, + "args": { + "External id": 1408057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531406824.623, "dur": 4.016, + "args": { + "External id": 1408058,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406833.870, "dur": 12.630, + "args": { + "External id": 1408059,"Record function id": 0, "Sequence number": 15109004, "Fwd thread id": 1, "Ev Idx": 570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406835.345, "dur": 7.980, + "args": { + "External id": 1408060,"Sequence number": 15109004, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 571 + } + }, + { + "ph": "f", "id": 62, "pid": 2338710, "tid": 2379450, "ts": 6410531406835.345, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406838.866, "dur": 4.293, + "args": { + "External id": 1408061,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406841.730, "dur": 1.322, + "args": { + "External id": 1408062,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406850.007, "dur": 124.992, + "args": { + "External id": 1408063,"Record function id": 0, "Sequence number": 15109003, "Fwd thread id": 1, "Ev Idx": 574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406850.767, "dur": 112.968, + "args": { + "External id": 1408064,"Sequence number": 15109003, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 575 + } + }, + { + "ph": "f", "id": 63, "pid": 2338710, "tid": 2379450, "ts": 6410531406850.767, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406854.023, "dur": 2.920, + "args": { + "External id": 1408065,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406854.755, "dur": 1.692, + "args": { + "External id": 1408066,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406855.627, "dur": 0.696, + "args": { + "External id": 1408067,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531406863.417, "dur": 39.923, + "args": { + "External id": 1408068,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406904.845, "dur": 5.458, + "args": { + "External id": 1408069,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406905.581, "dur": 4.063, + "args": { + "External id": 1408070,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406906.627, "dur": 2.866, + "args": { + "External id": 1408071,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531406911.648, "dur": 5.914, + "args": { + "External id": 1408072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531406913.154, "dur": 3.717, + "args": { + "External id": 1408073,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531406916.383, "dur": 0.390, + "args": { + "External id": 1408074,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531406920.382, "dur": 42.305, + "args": { + "External id": 1408075,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406980.731, "dur": 30.400, + "args": { + "External id": 1408076,"Record function id": 0, "Sequence number": 15109002, "Fwd thread id": 1, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531406981.900, "dur": 4.365, + "args": { + "External id": 1408077,"Sequence number": 15109002, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 588 + } + }, + { + "ph": "f", "id": 64, "pid": 2338710, "tid": 2379450, "ts": 6410531406981.900, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531406983.896, "dur": 2.190, + "args": { + "External id": 1408078,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531406984.720, "dur": 1.198, + "args": { + "External id": 1408079,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531406989.337, "dur": 19.029, + "args": { + "External id": 1408080,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531407015.631, "dur": 16.061, + "args": { + "External id": 1408081,"Record function id": 0, "Sequence number": 15109001, "Fwd thread id": 1, "Ev Idx": 592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531407016.864, "dur": 12.373, + "args": { + "External id": 1408082,"Sequence number": 15109001, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 593 + } + }, + { + "ph": "f", "id": 65, "pid": 2338710, "tid": 2379450, "ts": 6410531407016.864, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531407017.800, "dur": 11.198, + "args": { + "External id": 1408083,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531407018.742, "dur": 9.637, + "args": { + "External id": 1408084,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407025.280, "dur": 2.955, + "args": { + "External id": 1408085,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531407036.558, "dur": 5.335, + "args": { + "External id": 1408086,"Record function id": 0, "Ev Idx": 597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531407037.987, "dur": 3.343, + "args": { + "External id": 1408087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531407039.037, "dur": 1.955, + "args": { + "External id": 1408088,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531407039.669, "dur": 1.177, + "args": { + "External id": 1408089,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531407046.863, "dur": 522.937, + "args": { + "External id": 1408090,"Record function id": 0, "Sequence number": 15109000, "Fwd thread id": 1, "Ev Idx": 601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531407048.099, "dur": 474.885, + "args": { + "External id": 1408091,"Sequence number": 15109000, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 602 + } + }, + { + "ph": "f", "id": 66, "pid": 2338710, "tid": 2379450, "ts": 6410531407048.099, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531407134.408, "dur": 3.178, + "args": { + "External id": 1408092,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531407135.297, "dur": 1.898, + "args": { + "External id": 1408093,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531407158.232, "dur": 5.804, + "args": { + "External id": 1408094,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531407175.843, "dur": 2.353, + "args": { + "External id": 1408095,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531407375.595, "dur": 2.037, + "args": { + "External id": 1408096,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531407382.448, "dur": 59.186, + "args": { + "External id": 1408097,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407393.466, "dur": 0.872, + "args": { + "External id": 1408098,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531407450.323, "dur": 39.661, + "args": { + "External id": 1408099,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531407452.355, "dur": 37.379, + "args": { + "External id": 1408100,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407460.636, "dur": 4.916, + "args": { + "External id": 1408101,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531407467.456, "dur": 21.727, + "args": { + "External id": 1408102,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531407498.285, "dur": 5.446, + "args": { + "External id": 1408103,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531407499.414, "dur": 4.155, + "args": { + "External id": 1408104,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531407512.746, "dur": 1.869, + "args": { + "External id": 1408105,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531407513.479, "dur": 0.969, + "args": { + "External id": 1408106,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531407539.034, "dur": 22.811, + "args": { + "External id": 1408107,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531407585.817, "dur": 12.424, + "args": { + "External id": 1408108,"Record function id": 0, "Ev Idx": 619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531407590.552, "dur": 6.843, + "args": { + "External id": 1408109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531407593.148, "dur": 2.990, + "args": { + "External id": 1408110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531407594.081, "dur": 1.943, + "args": { + "External id": 1408111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531407606.042, "dur": 8.393, + "args": { + "External id": 1408112,"Record function id": 0, "Sequence number": 15108999, "Fwd thread id": 1, "Ev Idx": 623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531407607.628, "dur": 1.712, + "args": { + "External id": 1408113,"Sequence number": 15108999, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 624 + } + }, + { + "ph": "f", "id": 67, "pid": 2338710, "tid": 2379450, "ts": 6410531407607.628, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531407618.895, "dur": 533.132, + "args": { + "External id": 1408114,"Record function id": 0, "Sequence number": 15108998, "Fwd thread id": 1, "Ev Idx": 625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531407620.410, "dur": 514.158, + "args": { + "External id": 1408115,"Sequence number": 15108998, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 626 + } + }, + { + "ph": "f", "id": 68, "pid": 2338710, "tid": 2379450, "ts": 6410531407620.410, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531407659.911, "dur": 9.061, + "args": { + "External id": 1408116,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531407665.076, "dur": 3.564, + "args": { + "External id": 1408117,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531407672.589, "dur": 8.203, + "args": { + "External id": 1408118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531407674.660, "dur": 5.395, + "args": { + "External id": 1408119,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407678.828, "dur": 1.076, + "args": { + "External id": 1408120,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2379450, + "ts": 6410531407684.899, "dur": 101.894, + "args": { + "External id": 1408121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531407688.037, "dur": 2.871, + "args": { + "External id": 1408122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531407688.529, "dur": 1.799, + "args": { + "External id": 1408123,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407689.515, "dur": 0.708, + "args": { + "External id": 1408124,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2379450, + "ts": 6410531407692.016, "dur": 94.141, + "args": { + "External id": 1408125,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531407693.602, "dur": 91.570, + "args": { + "External id": 1408126,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531407791.372, "dur": 3.285, + "args": { + "External id": 1408127,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531407792.663, "dur": 1.841, + "args": { + "External id": 1408128,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531407835.173, "dur": 8.664, + "args": { + "External id": 1408129,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531407847.825, "dur": 1.914, + "args": { + "External id": 1408130,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531407850.445, "dur": 2.208, + "args": { + "External id": 1408131,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531407888.810, "dur": 2.192, + "args": { + "External id": 1408132,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531407889.507, "dur": 1.300, + "args": { + "External id": 1408133,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338710, "tid": 2379450, + "ts": 6410531407916.602, "dur": 188.590, + "args": { + "External id": 1408134,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410531407922.224, "dur": 9.660, + "args": { + "External id": 1408135,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407927.855, "dur": 3.099, + "args": { + "External id": 1408136,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531407933.346, "dur": 6.150, + "args": { + "External id": 1408137,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407938.151, "dur": 0.611, + "args": { + "External id": 1408138,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410531407941.099, "dur": 1.675, + "args": { + "External id": 1408139,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407941.942, "dur": 0.461, + "args": { + "External id": 1408140,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531407945.727, "dur": 2.342, + "args": { + "External id": 1408141,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407946.903, "dur": 0.454, + "args": { + "External id": 1408142,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531407954.712, "dur": 4.413, + "args": { + "External id": 1408143,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407955.835, "dur": 2.928, + "args": { + "External id": 1408144,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531407960.183, "dur": 7.899, + "args": { + "External id": 1408145,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531407966.038, "dur": 1.859, + "args": { + "External id": 1408146,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531407971.699, "dur": 3.730, + "args": { + "External id": 1408147,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531407974.681, "dur": 0.420, + "args": { + "External id": 1408148,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531407975.913, "dur": 4.669, + "args": { + "External id": 1408149,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531407976.595, "dur": 3.895, + "args": { + "External id": 1408150,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531407981.882, "dur": 58.470, + "args": { + "External id": 1408151,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408045.108, "dur": 1.531, + "args": { + "External id": 1408152,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531408047.302, "dur": 5.260, + "args": { + "External id": 1408153,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408051.266, "dur": 0.450, + "args": { + "External id": 1408154,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408055.128, "dur": 47.778, + "args": { + "External id": 1408155,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531408167.572, "dur": 13.961, + "args": { + "External id": 1408156,"Record function id": 0, "Ev Idx": 667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531408170.174, "dur": 10.429, + "args": { + "External id": 1408157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531408173.212, "dur": 6.444, + "args": { + "External id": 1408158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531408174.399, "dur": 5.132, + "args": { + "External id": 1408159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408185.923, "dur": 8.135, + "args": { + "External id": 1408160,"Record function id": 0, "Sequence number": 15108997, "Fwd thread id": 1, "Ev Idx": 671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408186.911, "dur": 4.423, + "args": { + "External id": 1408161,"Sequence number": 15108997, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 672 + } + }, + { + "ph": "f", "id": 69, "pid": 2338710, "tid": 2379450, "ts": 6410531408186.911, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531408189.186, "dur": 1.883, + "args": { + "External id": 1408162,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408189.694, "dur": 1.253, + "args": { + "External id": 1408163,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408198.089, "dur": 143.995, + "args": { + "External id": 1408164,"Record function id": 0, "Sequence number": 15108996, "Fwd thread id": 1, "Ev Idx": 675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408199.024, "dur": 134.934, + "args": { + "External id": 1408165,"Sequence number": 15108996, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 676 + } + }, + { + "ph": "f", "id": 70, "pid": 2338710, "tid": 2379450, "ts": 6410531408199.024, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531408205.109, "dur": 4.925, + "args": { + "External id": 1408166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531408206.904, "dur": 2.532, + "args": { + "External id": 1408167,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408208.316, "dur": 0.950, + "args": { + "External id": 1408168,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531408211.583, "dur": 58.896, + "args": { + "External id": 1408169,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531408272.078, "dur": 9.725, + "args": { + "External id": 1408170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531408272.717, "dur": 8.203, + "args": { + "External id": 1408171,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408279.688, "dur": 1.057, + "args": { + "External id": 1408172,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531408283.896, "dur": 7.227, + "args": { + "External id": 1408173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531408289.232, "dur": 1.416, + "args": { + "External id": 1408174,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408290.133, "dur": 0.419, + "args": { + "External id": 1408175,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531408291.669, "dur": 41.254, + "args": { + "External id": 1408176,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408347.814, "dur": 12.187, + "args": { + "External id": 1408177,"Record function id": 0, "Sequence number": 15108995, "Fwd thread id": 1, "Ev Idx": 688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408348.958, "dur": 9.247, + "args": { + "External id": 1408178,"Sequence number": 15108995, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 689 + } + }, + { + "ph": "f", "id": 71, "pid": 2338710, "tid": 2379450, "ts": 6410531408348.958, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531408350.527, "dur": 7.482, + "args": { + "External id": 1408179,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408356.416, "dur": 1.475, + "args": { + "External id": 1408180,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408364.046, "dur": 10.652, + "args": { + "External id": 1408181,"Record function id": 0, "Sequence number": 15108994, "Fwd thread id": 1, "Ev Idx": 692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408364.905, "dur": 6.746, + "args": { + "External id": 1408182,"Sequence number": 15108994, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 693 + } + }, + { + "ph": "f", "id": 72, "pid": 2338710, "tid": 2379450, "ts": 6410531408364.905, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531408365.893, "dur": 5.488, + "args": { + "External id": 1408183,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531408366.585, "dur": 4.238, + "args": { + "External id": 1408184,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408367.707, "dur": 3.012, + "args": { + "External id": 1408185,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531408379.350, "dur": 5.306, + "args": { + "External id": 1408186,"Record function id": 0, "Ev Idx": 697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531408380.489, "dur": 3.644, + "args": { + "External id": 1408187,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531408381.702, "dur": 2.142, + "args": { + "External id": 1408188,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531408382.482, "dur": 1.254, + "args": { + "External id": 1408189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408388.403, "dur": 11.480, + "args": { + "External id": 1408190,"Record function id": 0, "Sequence number": 15108993, "Fwd thread id": 1, "Ev Idx": 701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408389.459, "dur": 7.481, + "args": { + "External id": 1408191,"Sequence number": 15108993, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 702 + } + }, + { + "ph": "f", "id": 73, "pid": 2338710, "tid": 2379450, "ts": 6410531408389.459, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531408392.882, "dur": 3.875, + "args": { + "External id": 1408192,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408395.808, "dur": 0.842, + "args": { + "External id": 1408193,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408403.824, "dur": 135.908, + "args": { + "External id": 1408194,"Record function id": 0, "Sequence number": 15108992, "Fwd thread id": 1, "Ev Idx": 705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408404.688, "dur": 124.183, + "args": { + "External id": 1408195,"Sequence number": 15108992, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 706 + } + }, + { + "ph": "f", "id": 74, "pid": 2338710, "tid": 2379450, "ts": 6410531408404.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531408408.199, "dur": 5.092, + "args": { + "External id": 1408196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531408408.958, "dur": 3.820, + "args": { + "External id": 1408197,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408412.135, "dur": 0.475, + "args": { + "External id": 1408198,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531408413.988, "dur": 60.912, + "args": { + "External id": 1408199,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531408477.504, "dur": 4.563, + "args": { + "External id": 1408200,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531408478.632, "dur": 2.656, + "args": { + "External id": 1408201,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408480.083, "dur": 1.034, + "args": { + "External id": 1408202,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531408483.744, "dur": 8.201, + "args": { + "External id": 1408203,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531408485.103, "dur": 6.326, + "args": { + "External id": 1408204,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408490.847, "dur": 0.485, + "args": { + "External id": 1408205,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531408492.587, "dur": 35.363, + "args": { + "External id": 1408206,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408546.996, "dur": 37.913, + "args": { + "External id": 1408207,"Record function id": 0, "Sequence number": 15108991, "Fwd thread id": 1, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408548.232, "dur": 7.365, + "args": { + "External id": 1408208,"Sequence number": 15108991, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 719 + } + }, + { + "ph": "f", "id": 75, "pid": 2338710, "tid": 2379450, "ts": 6410531408548.232, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531408550.345, "dur": 5.079, + "args": { + "External id": 1408209,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408551.170, "dur": 4.087, + "args": { + "External id": 1408210,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531408558.853, "dur": 22.742, + "args": { + "External id": 1408211,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408589.857, "dur": 11.404, + "args": { + "External id": 1408212,"Record function id": 0, "Sequence number": 15108990, "Fwd thread id": 1, "Ev Idx": 723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531408591.137, "dur": 7.453, + "args": { + "External id": 1408213,"Sequence number": 15108990, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 724 + } + }, + { + "ph": "f", "id": 76, "pid": 2338710, "tid": 2379450, "ts": 6410531408591.137, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531408592.260, "dur": 6.080, + "args": { + "External id": 1408214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531408595.469, "dur": 2.134, + "args": { + "External id": 1408215,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408596.594, "dur": 0.820, + "args": { + "External id": 1408216,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531408608.403, "dur": 6.746, + "args": { + "External id": 1408217,"Record function id": 0, "Ev Idx": 728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531408610.337, "dur": 4.175, + "args": { + "External id": 1408218,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531408611.728, "dur": 2.297, + "args": { + "External id": 1408219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531408612.310, "dur": 1.581, + "args": { + "External id": 1408220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531408622.808, "dur": 537.684, + "args": { + "External id": 1408221,"Record function id": 0, "Sequence number": 15108989, "Fwd thread id": 1, "Ev Idx": 732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531408624.132, "dur": 487.880, + "args": { + "External id": 1408222,"Sequence number": 15108989, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 733 + } + }, + { + "ph": "f", "id": 77, "pid": 2338710, "tid": 2379450, "ts": 6410531408624.132, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2379450, + "ts": 6410531408653.423, "dur": 37.698, + "args": { + "External id": 1408223,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531408655.176, "dur": 35.708, + "args": { + "External id": 1408224,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531408658.430, "dur": 7.414, + "args": { + "External id": 1408225,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531408661.609, "dur": 3.498, + "args": { + "External id": 1408226,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531408667.297, "dur": 23.073, + "args": { + "External id": 1408227,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531408704.870, "dur": 6.678, + "args": { + "External id": 1408228,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408709.777, "dur": 1.604, + "args": { + "External id": 1408229,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531408716.467, "dur": 1.554, + "args": { + "External id": 1408230,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408716.974, "dur": 0.937, + "args": { + "External id": 1408231,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531408730.995, "dur": 2.813, + "args": { + "External id": 1408232,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531408749.132, "dur": 4.375, + "args": { + "External id": 1408233,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531408942.862, "dur": 2.376, + "args": { + "External id": 1408234,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531408950.221, "dur": 38.575, + "args": { + "External id": 1408235,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531408964.326, "dur": 0.884, + "args": { + "External id": 1408236,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531408995.220, "dur": 32.703, + "args": { + "External id": 1408237,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531408997.184, "dur": 30.486, + "args": { + "External id": 1408238,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409001.763, "dur": 7.303, + "args": { + "External id": 1408239,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531409010.792, "dur": 16.113, + "args": { + "External id": 1408240,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531409035.160, "dur": 5.564, + "args": { + "External id": 1408241,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531409039.177, "dur": 1.377, + "args": { + "External id": 1408242,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531409047.984, "dur": 2.520, + "args": { + "External id": 1408243,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531409049.149, "dur": 1.200, + "args": { + "External id": 1408244,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531409052.778, "dur": 46.524, + "args": { + "External id": 1408245,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531409096.698, "dur": 2.240, + "args": { + "External id": 1408246,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531409136.518, "dur": 22.057, + "args": { + "External id": 1408247,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531409176.481, "dur": 10.156, + "args": { + "External id": 1408248,"Record function id": 0, "Ev Idx": 759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531409178.907, "dur": 6.942, + "args": { + "External id": 1408249,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531409181.654, "dur": 3.054, + "args": { + "External id": 1408250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531409182.635, "dur": 1.940, + "args": { + "External id": 1408251,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409190.602, "dur": 8.513, + "args": { + "External id": 1408252,"Record function id": 0, "Sequence number": 15108988, "Fwd thread id": 1, "Ev Idx": 763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409191.682, "dur": 4.445, + "args": { + "External id": 1408253,"Sequence number": 15108988, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 764 + } + }, + { + "ph": "f", "id": 78, "pid": 2338710, "tid": 2379450, "ts": 6410531409191.682, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531409193.583, "dur": 2.288, + "args": { + "External id": 1408254,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531409194.518, "dur": 1.166, + "args": { + "External id": 1408255,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409206.022, "dur": 160.732, + "args": { + "External id": 1408256,"Record function id": 0, "Sequence number": 15108987, "Fwd thread id": 1, "Ev Idx": 767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409206.918, "dur": 150.255, + "args": { + "External id": 1408257,"Sequence number": 15108987, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 768 + } + }, + { + "ph": "f", "id": 79, "pid": 2338710, "tid": 2379450, "ts": 6410531409206.918, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531409211.744, "dur": 5.609, + "args": { + "External id": 1408258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531409213.671, "dur": 3.001, + "args": { + "External id": 1408259,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409215.328, "dur": 1.115, + "args": { + "External id": 1408260,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531409218.923, "dur": 76.880, + "args": { + "External id": 1408261,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531409297.391, "dur": 11.387, + "args": { + "External id": 1408262,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531409298.302, "dur": 9.678, + "args": { + "External id": 1408263,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409304.456, "dur": 3.364, + "args": { + "External id": 1408264,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531409310.562, "dur": 3.671, + "args": { + "External id": 1408265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531409311.963, "dur": 1.661, + "args": { + "External id": 1408266,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409313.007, "dur": 0.520, + "args": { + "External id": 1408267,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531409314.891, "dur": 41.425, + "args": { + "External id": 1408268,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409372.376, "dur": 10.347, + "args": { + "External id": 1408269,"Record function id": 0, "Sequence number": 15108986, "Fwd thread id": 1, "Ev Idx": 780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409373.618, "dur": 6.458, + "args": { + "External id": 1408270,"Sequence number": 15108986, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 781 + } + }, + { + "ph": "f", "id": 80, "pid": 2338710, "tid": 2379450, "ts": 6410531409373.618, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531409375.475, "dur": 4.428, + "args": { + "External id": 1408271,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531409378.407, "dur": 1.331, + "args": { + "External id": 1408272,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409389.272, "dur": 11.816, + "args": { + "External id": 1408273,"Record function id": 0, "Sequence number": 15108985, "Fwd thread id": 1, "Ev Idx": 784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409393.319, "dur": 4.563, + "args": { + "External id": 1408274,"Sequence number": 15108985, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 785 + } + }, + { + "ph": "f", "id": 81, "pid": 2338710, "tid": 2379450, "ts": 6410531409393.319, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531409394.625, "dur": 2.990, + "args": { + "External id": 1408275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531409395.492, "dur": 1.620, + "args": { + "External id": 1408276,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409396.568, "dur": 0.424, + "args": { + "External id": 1408277,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531409405.968, "dur": 5.715, + "args": { + "External id": 1408278,"Record function id": 0, "Ev Idx": 789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531409407.328, "dur": 3.797, + "args": { + "External id": 1408279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531409408.465, "dur": 2.372, + "args": { + "External id": 1408280,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531409409.066, "dur": 1.602, + "args": { + "External id": 1408281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409431.249, "dur": 13.890, + "args": { + "External id": 1408282,"Record function id": 0, "Sequence number": 15108984, "Fwd thread id": 1, "Ev Idx": 793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531409433.033, "dur": 8.507, + "args": { + "External id": 1408283,"Sequence number": 15108984, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 794 + } + }, + { + "ph": "f", "id": 82, "pid": 2338710, "tid": 2379450, "ts": 6410531409433.033, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531409438.121, "dur": 3.231, + "args": { + "External id": 1408284,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531409438.798, "dur": 2.260, + "args": { + "External id": 1408285,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531409451.443, "dur": 424.583, + "args": { + "External id": 1408286,"Record function id": 0, "Sequence number": 15108983, "Fwd thread id": 1, "Ev Idx": 797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531409454.816, "dur": 394.437, + "args": { + "External id": 1408287,"Sequence number": 15108983, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 798 + } + }, + { + "ph": "f", "id": 83, "pid": 2338710, "tid": 2379450, "ts": 6410531409454.816, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531409475.836, "dur": 8.602, + "args": { + "External id": 1408288,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409478.605, "dur": 5.345, + "args": { + "External id": 1408289,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531409487.185, "dur": 7.530, + "args": { + "External id": 1408290,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409490.148, "dur": 4.348, + "args": { + "External id": 1408291,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531409496.443, "dur": 4.048, + "args": { + "External id": 1408292,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409497.641, "dur": 2.654, + "args": { + "External id": 1408293,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531409534.573, "dur": 286.511, + "args": { + "External id": 1408294,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531409631.585, "dur": 3.500, + "args": { + "External id": 1408295,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531409639.152, "dur": 6.331, + "args": { + "External id": 1408296,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531409646.725, "dur": 2.141, + "args": { + "External id": 1408297,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531409652.407, "dur": 1.969, + "args": { + "External id": 1408298,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531409704.598, "dur": 2.465, + "args": { + "External id": 1408299,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531409705.419, "dur": 1.511, + "args": { + "External id": 1408300,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531409708.712, "dur": 36.307, + "args": { + "External id": 1408301,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409718.552, "dur": 1.595, + "args": { + "External id": 1408302,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531409746.308, "dur": 1.274, + "args": { + "External id": 1408303,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531409746.979, "dur": 0.481, + "args": { + "External id": 1408304,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531409748.346, "dur": 21.584, + "args": { + "External id": 1408305,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409750.070, "dur": 6.015, + "args": { + "External id": 1408306,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531409835.659, "dur": 3.489, + "args": { + "External id": 1408307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531409842.735, "dur": 0.666, + "args": { + "External id": 1408308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531409845.530, "dur": 0.691, + "args": { + "External id": 1408309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531409885.274, "dur": 316.868, + "args": { + "External id": 1408310,"Record function id": 0, "Sequence number": 15108982, "Fwd thread id": 1, "Ev Idx": 821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531409886.655, "dur": 303.488, + "args": { + "External id": 1408311,"Sequence number": 15108982, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 822 + } + }, + { + "ph": "f", "id": 84, "pid": 2338710, "tid": 2379450, "ts": 6410531409886.655, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531409910.126, "dur": 49.144, + "args": { + "External id": 1408312,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409915.754, "dur": 3.799, + "args": { + "External id": 1408313,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531409921.184, "dur": 37.440, + "args": { + "External id": 1408314,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531409971.401, "dur": 5.098, + "args": { + "External id": 1408315,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531409973.180, "dur": 2.973, + "args": { + "External id": 1408316,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531410215.805, "dur": 231.268, + "args": { + "External id": 1408317,"Record function id": 0, "Sequence number": 15108981, "Fwd thread id": 1, "Ev Idx": 828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531410218.155, "dur": 215.784, + "args": { + "External id": 1408318,"Sequence number": 15108981, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 829 + } + }, + { + "ph": "f", "id": 85, "pid": 2338710, "tid": 2379450, "ts": 6410531410218.155, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531410233.938, "dur": 58.244, + "args": { + "External id": 1408319,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410239.402, "dur": 5.501, + "args": { + "External id": 1408320,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531410246.239, "dur": 45.121, + "args": { + "External id": 1408321,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531410301.470, "dur": 4.567, + "args": { + "External id": 1408322,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410303.320, "dur": 2.335, + "args": { + "External id": 1408323,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410457.827, "dur": 20.993, + "args": { + "External id": 1408324,"Record function id": 0, "Sequence number": 15108980, "Fwd thread id": 1, "Ev Idx": 835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410460.244, "dur": 15.349, + "args": { + "External id": 1408325,"Sequence number": 15108980, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 836 + } + }, + { + "ph": "f", "id": 86, "pid": 2338710, "tid": 2379450, "ts": 6410531410460.244, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531410463.518, "dur": 11.729, + "args": { + "External id": 1408326,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531410467.099, "dur": 7.958, + "args": { + "External id": 1408327,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410483.358, "dur": 7.895, + "args": { + "External id": 1408328,"Record function id": 0, "Sequence number": 15108979, "Fwd thread id": 1, "Ev Idx": 839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410484.418, "dur": 3.665, + "args": { + "External id": 1408329,"Sequence number": 15108979, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 840 + } + }, + { + "ph": "f", "id": 87, "pid": 2338710, "tid": 2379450, "ts": 6410531410484.418, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531410485.776, "dur": 2.148, + "args": { + "External id": 1408330,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531410486.632, "dur": 1.082, + "args": { + "External id": 1408331,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410497.116, "dur": 11.709, + "args": { + "External id": 1408332,"Record function id": 0, "Sequence number": 15108978, "Fwd thread id": 1, "Ev Idx": 843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410498.088, "dur": 7.808, + "args": { + "External id": 1408333,"Sequence number": 15108978, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 844 + } + }, + { + "ph": "f", "id": 88, "pid": 2338710, "tid": 2379450, "ts": 6410531410498.088, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531410501.604, "dur": 4.122, + "args": { + "External id": 1408334,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531410504.603, "dur": 0.975, + "args": { + "External id": 1408335,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410513.096, "dur": 6.784, + "args": { + "External id": 1408336,"Record function id": 0, "Sequence number": 15108977, "Fwd thread id": 1, "Ev Idx": 847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410514.074, "dur": 3.184, + "args": { + "External id": 1408337,"Sequence number": 15108977, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 848 + } + }, + { + "ph": "f", "id": 89, "pid": 2338710, "tid": 2379450, "ts": 6410531410514.074, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531410515.243, "dur": 1.843, + "args": { + "External id": 1408338,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531410515.838, "dur": 1.100, + "args": { + "External id": 1408339,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410523.845, "dur": 194.659, + "args": { + "External id": 1408340,"Record function id": 0, "Sequence number": 15108976, "Fwd thread id": 1, "Ev Idx": 851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410525.026, "dur": 184.437, + "args": { + "External id": 1408341,"Sequence number": 15108976, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 852 + } + }, + { + "ph": "f", "id": 90, "pid": 2338710, "tid": 2379450, "ts": 6410531410525.026, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531410530.568, "dur": 10.099, + "args": { + "External id": 1408342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531410535.351, "dur": 4.549, + "args": { + "External id": 1408343,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410537.640, "dur": 1.931, + "args": { + "External id": 1408344,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531410542.676, "dur": 89.065, + "args": { + "External id": 1408345,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531410633.264, "dur": 7.501, + "args": { + "External id": 1408346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531410634.434, "dur": 5.409, + "args": { + "External id": 1408347,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410638.405, "dur": 1.201, + "args": { + "External id": 1408348,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531410645.705, "dur": 3.817, + "args": { + "External id": 1408349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531410647.372, "dur": 1.603, + "args": { + "External id": 1408350,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410648.255, "dur": 0.592, + "args": { + "External id": 1408351,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531410650.553, "dur": 57.674, + "args": { + "External id": 1408352,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410724.179, "dur": 10.369, + "args": { + "External id": 1408353,"Record function id": 0, "Sequence number": 15108975, "Fwd thread id": 1, "Ev Idx": 864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410725.321, "dur": 7.103, + "args": { + "External id": 1408354,"Sequence number": 15108975, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 865 + } + }, + { + "ph": "f", "id": 91, "pid": 2338710, "tid": 2379450, "ts": 6410531410725.321, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531410727.388, "dur": 4.870, + "args": { + "External id": 1408355,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531410730.578, "dur": 1.557, + "args": { + "External id": 1408356,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410740.917, "dur": 8.611, + "args": { + "External id": 1408357,"Record function id": 0, "Sequence number": 15108974, "Fwd thread id": 1, "Ev Idx": 868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410742.108, "dur": 4.988, + "args": { + "External id": 1408358,"Sequence number": 15108974, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 869 + } + }, + { + "ph": "f", "id": 92, "pid": 2338710, "tid": 2379450, "ts": 6410531410742.108, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531410743.292, "dur": 3.558, + "args": { + "External id": 1408359,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531410744.495, "dur": 1.799, + "args": { + "External id": 1408360,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410745.474, "dur": 0.689, + "args": { + "External id": 1408361,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531410756.361, "dur": 10.680, + "args": { + "External id": 1408362,"Record function id": 0, "Ev Idx": 873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531410758.106, "dur": 8.093, + "args": { + "External id": 1408363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531410761.138, "dur": 4.571, + "args": { + "External id": 1408364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531410762.511, "dur": 3.093, + "args": { + "External id": 1408365,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410770.599, "dur": 12.124, + "args": { + "External id": 1408366,"Record function id": 0, "Sequence number": 15108973, "Fwd thread id": 1, "Ev Idx": 877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410771.488, "dur": 8.472, + "args": { + "External id": 1408367,"Sequence number": 15108973, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 878 + } + }, + { + "ph": "f", "id": 93, "pid": 2338710, "tid": 2379450, "ts": 6410531410771.488, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531410775.634, "dur": 4.167, + "args": { + "External id": 1408368,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531410778.728, "dur": 0.896, + "args": { + "External id": 1408369,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410786.333, "dur": 125.449, + "args": { + "External id": 1408370,"Record function id": 0, "Sequence number": 15108972, "Fwd thread id": 1, "Ev Idx": 881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410787.177, "dur": 115.731, + "args": { + "External id": 1408371,"Sequence number": 15108972, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 882 + } + }, + { + "ph": "f", "id": 94, "pid": 2338710, "tid": 2379450, "ts": 6410531410787.177, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531410791.142, "dur": 5.199, + "args": { + "External id": 1408372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531410791.768, "dur": 4.093, + "args": { + "External id": 1408373,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410794.974, "dur": 0.758, + "args": { + "External id": 1408374,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531410797.197, "dur": 34.175, + "args": { + "External id": 1408375,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531410832.637, "dur": 12.126, + "args": { + "External id": 1408376,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531410840.399, "dur": 3.690, + "args": { + "External id": 1408377,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410841.500, "dur": 2.388, + "args": { + "External id": 1408378,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531410846.528, "dur": 10.615, + "args": { + "External id": 1408379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531410848.209, "dur": 8.369, + "args": { + "External id": 1408380,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410854.017, "dur": 2.447, + "args": { + "External id": 1408381,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531410857.854, "dur": 44.267, + "args": { + "External id": 1408382,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410917.264, "dur": 42.769, + "args": { + "External id": 1408383,"Record function id": 0, "Sequence number": 15108971, "Fwd thread id": 1, "Ev Idx": 894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410918.249, "dur": 4.210, + "args": { + "External id": 1408384,"Sequence number": 15108971, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 895 + } + }, + { + "ph": "f", "id": 95, "pid": 2338710, "tid": 2379450, "ts": 6410531410918.249, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531410919.928, "dur": 2.371, + "args": { + "External id": 1408385,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531410920.955, "dur": 1.196, + "args": { + "External id": 1408386,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531410930.144, "dur": 26.760, + "args": { + "External id": 1408387,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410966.791, "dur": 18.367, + "args": { + "External id": 1408388,"Record function id": 0, "Sequence number": 15108970, "Fwd thread id": 1, "Ev Idx": 899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531410967.819, "dur": 14.864, + "args": { + "External id": 1408389,"Sequence number": 15108970, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 900 + } + }, + { + "ph": "f", "id": 96, "pid": 2338710, "tid": 2379450, "ts": 6410531410967.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531410971.203, "dur": 11.198, + "args": { + "External id": 1408390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531410972.275, "dur": 9.397, + "args": { + "External id": 1408391,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531410980.968, "dur": 0.576, + "args": { + "External id": 1408392,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531410989.856, "dur": 6.449, + "args": { + "External id": 1408393,"Record function id": 0, "Ev Idx": 904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531410991.367, "dur": 4.314, + "args": { + "External id": 1408394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531410992.898, "dur": 2.314, + "args": { + "External id": 1408395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531410993.653, "dur": 1.417, + "args": { + "External id": 1408396,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411002.535, "dur": 9.163, + "args": { + "External id": 1408397,"Record function id": 0, "Sequence number": 15108969, "Fwd thread id": 1, "Ev Idx": 908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411003.526, "dur": 5.477, + "args": { + "External id": 1408398,"Sequence number": 15108969, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 909 + } + }, + { + "ph": "f", "id": 97, "pid": 2338710, "tid": 2379450, "ts": 6410531411003.526, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531411004.644, "dur": 4.197, + "args": { + "External id": 1408399,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531411007.634, "dur": 1.042, + "args": { + "External id": 1408400,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411015.465, "dur": 172.079, + "args": { + "External id": 1408401,"Record function id": 0, "Sequence number": 15108968, "Fwd thread id": 1, "Ev Idx": 912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411016.328, "dur": 158.150, + "args": { + "External id": 1408402,"Sequence number": 15108968, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 913 + } + }, + { + "ph": "f", "id": 98, "pid": 2338710, "tid": 2379450, "ts": 6410531411016.328, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531411019.386, "dur": 2.574, + "args": { + "External id": 1408403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531411019.975, "dur": 1.514, + "args": { + "External id": 1408404,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531411020.737, "dur": 0.586, + "args": { + "External id": 1408405,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531411022.851, "dur": 84.437, + "args": { + "External id": 1408406,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531411112.944, "dur": 7.390, + "args": { + "External id": 1408407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531411114.033, "dur": 5.295, + "args": { + "External id": 1408408,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531411118.206, "dur": 0.949, + "args": { + "External id": 1408409,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531411122.124, "dur": 3.678, + "args": { + "External id": 1408410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531411123.858, "dur": 1.418, + "args": { + "External id": 1408411,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531411124.682, "dur": 0.512, + "args": { + "External id": 1408412,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531411129.653, "dur": 43.955, + "args": { + "External id": 1408413,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411195.491, "dur": 34.147, + "args": { + "External id": 1408414,"Record function id": 0, "Sequence number": 15108967, "Fwd thread id": 1, "Ev Idx": 925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411196.635, "dur": 6.674, + "args": { + "External id": 1408415,"Sequence number": 15108967, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 926 + } + }, + { + "ph": "f", "id": 99, "pid": 2338710, "tid": 2379450, "ts": 6410531411196.635, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531411198.438, "dur": 4.687, + "args": { + "External id": 1408416,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531411201.464, "dur": 1.539, + "args": { + "External id": 1408417,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531411206.562, "dur": 20.360, + "args": { + "External id": 1408418,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411234.215, "dur": 10.901, + "args": { + "External id": 1408419,"Record function id": 0, "Sequence number": 15108966, "Fwd thread id": 1, "Ev Idx": 930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411235.206, "dur": 6.925, + "args": { + "External id": 1408420,"Sequence number": 15108966, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 931 + } + }, + { + "ph": "f", "id": 100, "pid": 2338710, "tid": 2379450, "ts": 6410531411235.206, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531411236.313, "dur": 5.540, + "args": { + "External id": 1408421,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531411236.942, "dur": 4.368, + "args": { + "External id": 1408422,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531411240.517, "dur": 0.664, + "args": { + "External id": 1408423,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531411249.864, "dur": 6.795, + "args": { + "External id": 1408424,"Record function id": 0, "Ev Idx": 935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531411251.622, "dur": 4.424, + "args": { + "External id": 1408425,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531411253.202, "dur": 2.428, + "args": { + "External id": 1408426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531411253.989, "dur": 1.514, + "args": { + "External id": 1408427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531411261.573, "dur": 452.964, + "args": { + "External id": 1408428,"Record function id": 0, "Sequence number": 15108965, "Fwd thread id": 1, "Ev Idx": 939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531411262.869, "dur": 413.645, + "args": { + "External id": 1408429,"Sequence number": 15108965, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 940 + } + }, + { + "ph": "f", "id": 101, "pid": 2338710, "tid": 2379450, "ts": 6410531411262.869, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531411306.946, "dur": 2.613, + "args": { + "External id": 1408430,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531411307.824, "dur": 1.497, + "args": { + "External id": 1408431,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531411326.543, "dur": 7.220, + "args": { + "External id": 1408432,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531411347.142, "dur": 3.009, + "args": { + "External id": 1408433,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531411549.145, "dur": 3.359, + "args": { + "External id": 1408434,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531411557.478, "dur": 45.446, + "args": { + "External id": 1408435,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531411574.178, "dur": 0.949, + "args": { + "External id": 1408436,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531411609.740, "dur": 36.053, + "args": { + "External id": 1408437,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531411612.164, "dur": 33.387, + "args": { + "External id": 1408438,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531411616.929, "dur": 6.838, + "args": { + "External id": 1408439,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531411625.736, "dur": 19.237, + "args": { + "External id": 1408440,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531411653.663, "dur": 2.916, + "args": { + "External id": 1408441,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531411655.055, "dur": 1.414, + "args": { + "External id": 1408442,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531411666.454, "dur": 2.194, + "args": { + "External id": 1408443,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531411667.223, "dur": 1.314, + "args": { + "External id": 1408444,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531411691.224, "dur": 18.074, + "args": { + "External id": 1408445,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531411732.042, "dur": 15.277, + "args": { + "External id": 1408446,"Record function id": 0, "Ev Idx": 957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531411734.173, "dur": 12.323, + "args": { + "External id": 1408447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531411736.577, "dur": 8.404, + "args": { + "External id": 1408448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531411743.141, "dur": 1.674, + "args": { + "External id": 1408449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411751.649, "dur": 6.381, + "args": { + "External id": 1408450,"Record function id": 0, "Sequence number": 15108964, "Fwd thread id": 1, "Ev Idx": 961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531411752.831, "dur": 1.383, + "args": { + "External id": 1408451,"Sequence number": 15108964, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 962 + } + }, + { + "ph": "f", "id": 102, "pid": 2338710, "tid": 2379450, "ts": 6410531411752.831, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531411762.713, "dur": 539.467, + "args": { + "External id": 1408452,"Record function id": 0, "Sequence number": 15108963, "Fwd thread id": 1, "Ev Idx": 963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531411764.025, "dur": 521.524, + "args": { + "External id": 1408453,"Sequence number": 15108963, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 964 + } + }, + { + "ph": "f", "id": 103, "pid": 2338710, "tid": 2379450, "ts": 6410531411764.025, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531411798.182, "dur": 12.021, + "args": { + "External id": 1408454,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531411806.377, "dur": 3.507, + "args": { + "External id": 1408455,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531411813.753, "dur": 7.842, + "args": { + "External id": 1408456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531411817.934, "dur": 2.891, + "args": { + "External id": 1408457,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531411819.643, "dur": 0.918, + "args": { + "External id": 1408458,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2379450, + "ts": 6410531411825.675, "dur": 103.654, + "args": { + "External id": 1408459,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531411826.749, "dur": 5.221, + "args": { + "External id": 1408460,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531411827.387, "dur": 4.031, + "args": { + "External id": 1408461,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531411828.170, "dur": 3.134, + "args": { + "External id": 1408462,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2379450, + "ts": 6410531411835.472, "dur": 93.370, + "args": { + "External id": 1408463,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531411837.043, "dur": 90.593, + "args": { + "External id": 1408464,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531411933.996, "dur": 5.704, + "args": { + "External id": 1408465,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531411938.064, "dur": 1.515, + "args": { + "External id": 1408466,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531411978.958, "dur": 6.673, + "args": { + "External id": 1408467,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531411986.836, "dur": 2.422, + "args": { + "External id": 1408468,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531411990.061, "dur": 2.534, + "args": { + "External id": 1408469,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412033.818, "dur": 2.408, + "args": { + "External id": 1408470,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412034.828, "dur": 1.215, + "args": { + "External id": 1408471,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338710, "tid": 2379450, + "ts": 6410531412101.317, "dur": 161.647, + "args": { + "External id": 1408472,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410531412107.038, "dur": 6.600, + "args": { + "External id": 1408473,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412110.819, "dur": 1.560, + "args": { + "External id": 1408474,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531412117.998, "dur": 9.032, + "args": { + "External id": 1408475,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412123.166, "dur": 2.900, + "args": { + "External id": 1408476,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410531412128.866, "dur": 4.315, + "args": { + "External id": 1408477,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412132.445, "dur": 0.372, + "args": { + "External id": 1408478,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531412133.733, "dur": 5.553, + "args": { + "External id": 1408479,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412137.944, "dur": 0.605, + "args": { + "External id": 1408480,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531412145.561, "dur": 4.470, + "args": { + "External id": 1408481,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412149.023, "dur": 0.657, + "args": { + "External id": 1408482,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412150.894, "dur": 8.750, + "args": { + "External id": 1408483,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531412156.684, "dur": 2.786, + "args": { + "External id": 1408484,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531412160.295, "dur": 1.746, + "args": { + "External id": 1408485,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412161.364, "dur": 0.333, + "args": { + "External id": 1408486,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412165.113, "dur": 4.626, + "args": { + "External id": 1408487,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412165.531, "dur": 4.095, + "args": { + "External id": 1408488,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531412171.216, "dur": 71.308, + "args": { + "External id": 1408489,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 1000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412247.590, "dur": 3.850, + "args": { + "External id": 1408490,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 1001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531412252.071, "dur": 5.876, + "args": { + "External id": 1408491,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 1002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412256.625, "dur": 0.436, + "args": { + "External id": 1408492,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 1003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412260.635, "dur": 1.064, + "args": { + "External id": 1408493,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 1004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531412316.312, "dur": 10.616, + "args": { + "External id": 1408494,"Record function id": 0, "Ev Idx": 1005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531412318.596, "dur": 7.245, + "args": { + "External id": 1408495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531412321.409, "dur": 3.377, + "args": { + "External id": 1408496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531412322.557, "dur": 2.093, + "args": { + "External id": 1408497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412331.249, "dur": 12.728, + "args": { + "External id": 1408498,"Record function id": 0, "Sequence number": 15108962, "Fwd thread id": 1, "Ev Idx": 1009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412332.188, "dur": 8.593, + "args": { + "External id": 1408499,"Sequence number": 15108962, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 1010 + } + }, + { + "ph": "f", "id": 104, "pid": 2338710, "tid": 2379450, "ts": 6410531412332.188, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412334.245, "dur": 6.333, + "args": { + "External id": 1408500,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412339.576, "dur": 0.863, + "args": { + "External id": 1408501,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412348.013, "dur": 187.162, + "args": { + "External id": 1408502,"Record function id": 0, "Sequence number": 15108961, "Fwd thread id": 1, "Ev Idx": 1013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412348.884, "dur": 177.245, + "args": { + "External id": 1408503,"Sequence number": 15108961, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1014 + } + }, + { + "ph": "f", "id": 105, "pid": 2338710, "tid": 2379450, "ts": 6410531412348.884, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531412353.302, "dur": 4.299, + "args": { + "External id": 1408504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531412355.004, "dur": 1.946, + "args": { + "External id": 1408505,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 1016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412356.291, "dur": 0.483, + "args": { + "External id": 1408506,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531412361.917, "dur": 49.744, + "args": { + "External id": 1408507,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 1018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531412413.172, "dur": 22.124, + "args": { + "External id": 1408508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531412413.679, "dur": 20.090, + "args": { + "External id": 1408509,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412431.445, "dur": 1.786, + "args": { + "External id": 1408510,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531412437.661, "dur": 34.887, + "args": { + "External id": 1408511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531412439.173, "dur": 32.604, + "args": { + "External id": 1408512,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412471.025, "dur": 0.593, + "args": { + "External id": 1408513,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531412473.264, "dur": 51.565, + "args": { + "External id": 1408514,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 1025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412545.153, "dur": 6.823, + "args": { + "External id": 1408515,"Record function id": 0, "Sequence number": 15108960, "Fwd thread id": 1, "Ev Idx": 1026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412546.286, "dur": 4.183, + "args": { + "External id": 1408516,"Sequence number": 15108960, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1027 + } + }, + { + "ph": "f", "id": 106, "pid": 2338710, "tid": 2379450, "ts": 6410531412546.286, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412548.184, "dur": 2.122, + "args": { + "External id": 1408517,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412548.772, "dur": 1.420, + "args": { + "External id": 1408518,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412555.874, "dur": 10.795, + "args": { + "External id": 1408519,"Record function id": 0, "Sequence number": 15108959, "Fwd thread id": 1, "Ev Idx": 1030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412556.729, "dur": 6.785, + "args": { + "External id": 1408520,"Sequence number": 15108959, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1031 + } + }, + { + "ph": "f", "id": 107, "pid": 2338710, "tid": 2379450, "ts": 6410531412556.729, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531412557.524, "dur": 5.730, + "args": { + "External id": 1408521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531412558.263, "dur": 4.457, + "args": { + "External id": 1408522,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412562.103, "dur": 0.455, + "args": { + "External id": 1408523,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531412573.920, "dur": 6.178, + "args": { + "External id": 1408524,"Record function id": 0, "Ev Idx": 1035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531412575.391, "dur": 4.114, + "args": { + "External id": 1408525,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531412576.978, "dur": 2.218, + "args": { + "External id": 1408526,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531412577.501, "dur": 1.558, + "args": { + "External id": 1408527,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412583.619, "dur": 6.699, + "args": { + "External id": 1408528,"Record function id": 0, "Sequence number": 15108958, "Fwd thread id": 1, "Ev Idx": 1039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412584.752, "dur": 3.135, + "args": { + "External id": 1408529,"Sequence number": 15108958, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 1040 + } + }, + { + "ph": "f", "id": 108, "pid": 2338710, "tid": 2379450, "ts": 6410531412584.752, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412586.163, "dur": 1.566, + "args": { + "External id": 1408530,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412586.601, "dur": 0.883, + "args": { + "External id": 1408531,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412594.160, "dur": 120.575, + "args": { + "External id": 1408532,"Record function id": 0, "Sequence number": 15108957, "Fwd thread id": 1, "Ev Idx": 1043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412595.190, "dur": 107.792, + "args": { + "External id": 1408533,"Sequence number": 15108957, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1044 + } + }, + { + "ph": "f", "id": 109, "pid": 2338710, "tid": 2379450, "ts": 6410531412595.190, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531412601.507, "dur": 2.661, + "args": { + "External id": 1408534,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531412602.044, "dur": 1.627, + "args": { + "External id": 1408535,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412602.840, "dur": 0.706, + "args": { + "External id": 1408536,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531412605.117, "dur": 42.015, + "args": { + "External id": 1408537,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 1048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531412648.640, "dur": 8.369, + "args": { + "External id": 1408538,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531412649.185, "dur": 7.200, + "args": { + "External id": 1408539,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412655.450, "dur": 0.781, + "args": { + "External id": 1408540,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531412658.417, "dur": 5.974, + "args": { + "External id": 1408541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531412660.069, "dur": 3.703, + "args": { + "External id": 1408542,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412660.785, "dur": 2.889, + "args": { + "External id": 1408543,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531412664.949, "dur": 37.011, + "args": { + "External id": 1408544,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 1055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412720.157, "dur": 41.018, + "args": { + "External id": 1408545,"Record function id": 0, "Sequence number": 15108956, "Fwd thread id": 1, "Ev Idx": 1056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412721.172, "dur": 8.506, + "args": { + "External id": 1408546,"Sequence number": 15108956, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1057 + } + }, + { + "ph": "f", "id": 110, "pid": 2338710, "tid": 2379450, "ts": 6410531412721.172, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412722.918, "dur": 6.599, + "args": { + "External id": 1408547,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412727.778, "dur": 1.622, + "args": { + "External id": 1408548,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531412732.936, "dur": 24.818, + "args": { + "External id": 1408549,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412765.725, "dur": 8.022, + "args": { + "External id": 1408550,"Record function id": 0, "Sequence number": 15108955, "Fwd thread id": 1, "Ev Idx": 1061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531412766.819, "dur": 4.462, + "args": { + "External id": 1408551,"Sequence number": 15108955, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1062 + } + }, + { + "ph": "f", "id": 111, "pid": 2338710, "tid": 2379450, "ts": 6410531412766.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531412767.644, "dur": 3.386, + "args": { + "External id": 1408552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531412768.420, "dur": 1.993, + "args": { + "External id": 1408553,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531412769.491, "dur": 0.727, + "args": { + "External id": 1408554,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531412778.212, "dur": 7.972, + "args": { + "External id": 1408555,"Record function id": 0, "Ev Idx": 1066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531412779.458, "dur": 6.176, + "args": { + "External id": 1408556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531412780.680, "dur": 4.555, + "args": { + "External id": 1408557,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531412783.973, "dur": 1.105, + "args": { + "External id": 1408558,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531412790.838, "dur": 565.585, + "args": { + "External id": 1408559,"Record function id": 0, "Sequence number": 15108954, "Fwd thread id": 1, "Ev Idx": 1070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531412792.350, "dur": 515.495, + "args": { + "External id": 1408560,"Sequence number": 15108954, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 1071 + } + }, + { + "ph": "f", "id": 112, "pid": 2338710, "tid": 2379450, "ts": 6410531412792.350, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2379450, + "ts": 6410531412819.393, "dur": 41.445, + "args": { + "External id": 1408561,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531412821.223, "dur": 39.354, + "args": { + "External id": 1408562,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531412826.897, "dur": 7.135, + "args": { + "External id": 1408563,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 1074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531412829.569, "dur": 3.720, + "args": { + "External id": 1408564,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531412835.478, "dur": 24.545, + "args": { + "External id": 1408565,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412874.610, "dur": 2.243, + "args": { + "External id": 1408566,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412875.370, "dur": 1.288, + "args": { + "External id": 1408567,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531412881.279, "dur": 6.619, + "args": { + "External id": 1408568,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531412884.753, "dur": 3.022, + "args": { + "External id": 1408569,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531412901.413, "dur": 2.677, + "args": { + "External id": 1408570,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531412918.600, "dur": 2.896, + "args": { + "External id": 1408571,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531413165.055, "dur": 4.418, + "args": { + "External id": 1408572,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 1083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531413174.699, "dur": 46.667, + "args": { + "External id": 1408573,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 1084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413191.961, "dur": 0.933, + "args": { + "External id": 1408574,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531413228.923, "dur": 37.875, + "args": { + "External id": 1408575,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 1086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531413233.393, "dur": 33.159, + "args": { + "External id": 1408576,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 1087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413238.112, "dur": 7.358, + "args": { + "External id": 1408577,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531413247.449, "dur": 18.534, + "args": { + "External id": 1408578,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 1089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531413271.989, "dur": 2.663, + "args": { + "External id": 1408579,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 1090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531413273.046, "dur": 1.487, + "args": { + "External id": 1408580,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 1091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531413282.554, "dur": 7.465, + "args": { + "External id": 1408581,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531413288.490, "dur": 1.422, + "args": { + "External id": 1408582,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531413292.348, "dur": 4.451, + "args": { + "External id": 1408583,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531413292.993, "dur": 3.700, + "args": { + "External id": 1408584,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531413334.054, "dur": 20.611, + "args": { + "External id": 1408585,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531413372.900, "dur": 11.883, + "args": { + "External id": 1408586,"Record function id": 0, "Ev Idx": 1097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531413375.553, "dur": 8.305, + "args": { + "External id": 1408587,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531413378.920, "dur": 3.866, + "args": { + "External id": 1408588,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531413380.199, "dur": 2.466, + "args": { + "External id": 1408589,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413389.005, "dur": 14.510, + "args": { + "External id": 1408590,"Record function id": 0, "Sequence number": 15108953, "Fwd thread id": 1, "Ev Idx": 1101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413390.378, "dur": 9.044, + "args": { + "External id": 1408591,"Sequence number": 15108953, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1102 + } + }, + { + "ph": "f", "id": 113, "pid": 2338710, "tid": 2379450, "ts": 6410531413390.378, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531413392.675, "dur": 6.498, + "args": { + "External id": 1408592,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531413397.671, "dur": 1.362, + "args": { + "External id": 1408593,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413407.698, "dur": 234.395, + "args": { + "External id": 1408594,"Record function id": 0, "Sequence number": 15108952, "Fwd thread id": 1, "Ev Idx": 1105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413408.971, "dur": 221.445, + "args": { + "External id": 1408595,"Sequence number": 15108952, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1106 + } + }, + { + "ph": "f", "id": 114, "pid": 2338710, "tid": 2379450, "ts": 6410531413408.971, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531413413.126, "dur": 27.577, + "args": { + "External id": 1408596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531413435.444, "dur": 4.242, + "args": { + "External id": 1408597,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 1108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413437.709, "dur": 1.503, + "args": { + "External id": 1408598,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531413444.977, "dur": 98.362, + "args": { + "External id": 1408599,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 1110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531413545.182, "dur": 4.529, + "args": { + "External id": 1408600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531413546.293, "dur": 2.627, + "args": { + "External id": 1408601,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413547.660, "dur": 1.068, + "args": { + "External id": 1408602,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531413551.718, "dur": 17.628, + "args": { + "External id": 1408603,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531413562.513, "dur": 6.314, + "args": { + "External id": 1408604,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413567.857, "dur": 0.850, + "args": { + "External id": 1408605,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531413570.320, "dur": 59.051, + "args": { + "External id": 1408606,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 1117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413652.976, "dur": 10.933, + "args": { + "External id": 1408607,"Record function id": 0, "Sequence number": 15108951, "Fwd thread id": 1, "Ev Idx": 1118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413654.507, "dur": 6.750, + "args": { + "External id": 1408608,"Sequence number": 15108951, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1119 + } + }, + { + "ph": "f", "id": 115, "pid": 2338710, "tid": 2379450, "ts": 6410531413654.507, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531413656.161, "dur": 4.912, + "args": { + "External id": 1408609,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531413656.713, "dur": 4.223, + "args": { + "External id": 1408610,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413668.008, "dur": 12.731, + "args": { + "External id": 1408611,"Record function id": 0, "Sequence number": 15108950, "Fwd thread id": 1, "Ev Idx": 1122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413669.196, "dur": 8.937, + "args": { + "External id": 1408612,"Sequence number": 15108950, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1123 + } + }, + { + "ph": "f", "id": 116, "pid": 2338710, "tid": 2379450, "ts": 6410531413669.196, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531413670.164, "dur": 7.724, + "args": { + "External id": 1408613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531413670.873, "dur": 6.438, + "args": { + "External id": 1408614,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413676.684, "dur": 0.456, + "args": { + "External id": 1408615,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531413685.613, "dur": 7.384, + "args": { + "External id": 1408616,"Record function id": 0, "Ev Idx": 1127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531413687.150, "dur": 5.199, + "args": { + "External id": 1408617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531413688.855, "dur": 2.996, + "args": { + "External id": 1408618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531413690.049, "dur": 1.651, + "args": { + "External id": 1408619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413696.501, "dur": 7.709, + "args": { + "External id": 1408620,"Record function id": 0, "Sequence number": 15108949, "Fwd thread id": 1, "Ev Idx": 1131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531413697.488, "dur": 3.667, + "args": { + "External id": 1408621,"Sequence number": 15108949, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1132 + } + }, + { + "ph": "f", "id": 117, "pid": 2338710, "tid": 2379450, "ts": 6410531413697.488, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531413699.013, "dur": 1.967, + "args": { + "External id": 1408622,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531413699.540, "dur": 1.278, + "args": { + "External id": 1408623,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531413709.165, "dur": 518.549, + "args": { + "External id": 1408624,"Record function id": 0, "Sequence number": 15108948, "Fwd thread id": 1, "Ev Idx": 1135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531413710.363, "dur": 488.800, + "args": { + "External id": 1408625,"Sequence number": 15108948, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1136 + } + }, + { + "ph": "f", "id": 118, "pid": 2338710, "tid": 2379450, "ts": 6410531413710.363, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531413730.778, "dur": 11.967, + "args": { + "External id": 1408626,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 1137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413737.747, "dur": 4.453, + "args": { + "External id": 1408627,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531413744.992, "dur": 3.315, + "args": { + "External id": 1408628,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413746.019, "dur": 1.954, + "args": { + "External id": 1408629,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531413753.433, "dur": 7.456, + "args": { + "External id": 1408630,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531413756.565, "dur": 4.125, + "args": { + "External id": 1408631,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531413792.786, "dur": 373.799, + "args": { + "External id": 1408632,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531413891.155, "dur": 5.636, + "args": { + "External id": 1408633,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531413898.847, "dur": 4.918, + "args": { + "External id": 1408634,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531413907.425, "dur": 2.463, + "args": { + "External id": 1408635,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531413910.914, "dur": 4.160, + "args": { + "External id": 1408636,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531414002.198, "dur": 2.896, + "args": { + "External id": 1408637,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531414003.396, "dur": 1.596, + "args": { + "External id": 1408638,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531414009.281, "dur": 30.150, + "args": { + "External id": 1408639,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414014.682, "dur": 1.358, + "args": { + "External id": 1408640,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531414043.406, "dur": 1.632, + "args": { + "External id": 1408641,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531414044.274, "dur": 0.666, + "args": { + "External id": 1408642,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531414048.237, "dur": 62.364, + "args": { + "External id": 1408643,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414052.274, "dur": 0.591, + "args": { + "External id": 1408644,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531414182.978, "dur": 5.251, + "args": { + "External id": 1408645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531414191.717, "dur": 0.732, + "args": { + "External id": 1408646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531414194.785, "dur": 0.829, + "args": { + "External id": 1408647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531414241.484, "dur": 309.665, + "args": { + "External id": 1408648,"Record function id": 0, "Sequence number": 15108947, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531414243.493, "dur": 296.528, + "args": { + "External id": 1408649,"Sequence number": 15108947, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1160 + } + }, + { + "ph": "f", "id": 119, "pid": 2338710, "tid": 2379450, "ts": 6410531414243.493, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531414267.880, "dur": 61.511, + "args": { + "External id": 1408650,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414271.760, "dur": 5.350, + "args": { + "External id": 1408651,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531414279.609, "dur": 49.087, + "args": { + "External id": 1408652,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 1163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531414341.169, "dur": 8.335, + "args": { + "External id": 1408653,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414345.975, "dur": 3.066, + "args": { + "External id": 1408654,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531414562.873, "dur": 201.198, + "args": { + "External id": 1408655,"Record function id": 0, "Sequence number": 15108946, "Fwd thread id": 1, "Ev Idx": 1166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531414564.940, "dur": 191.100, + "args": { + "External id": 1408656,"Sequence number": 15108946, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1167 + } + }, + { + "ph": "f", "id": 120, "pid": 2338710, "tid": 2379450, "ts": 6410531414564.940, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531414580.156, "dur": 55.426, + "args": { + "External id": 1408657,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414583.012, "dur": 6.645, + "args": { + "External id": 1408658,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531414591.156, "dur": 43.858, + "args": { + "External id": 1408659,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 1170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531414644.525, "dur": 8.483, + "args": { + "External id": 1408660,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 1171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414649.212, "dur": 3.417, + "args": { + "External id": 1408661,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414771.927, "dur": 16.877, + "args": { + "External id": 1408662,"Record function id": 0, "Sequence number": 15108945, "Fwd thread id": 1, "Ev Idx": 1173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414773.972, "dur": 10.753, + "args": { + "External id": 1408663,"Sequence number": 15108945, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1174 + } + }, + { + "ph": "f", "id": 121, "pid": 2338710, "tid": 2379450, "ts": 6410531414773.972, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531414776.896, "dur": 7.519, + "args": { + "External id": 1408664,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531414778.659, "dur": 5.549, + "args": { + "External id": 1408665,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414793.043, "dur": 13.597, + "args": { + "External id": 1408666,"Record function id": 0, "Sequence number": 15108944, "Fwd thread id": 1, "Ev Idx": 1177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414796.840, "dur": 6.543, + "args": { + "External id": 1408667,"Sequence number": 15108944, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1178 + } + }, + { + "ph": "f", "id": 122, "pid": 2338710, "tid": 2379450, "ts": 6410531414796.840, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531414798.582, "dur": 4.610, + "args": { + "External id": 1408668,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531414801.783, "dur": 1.221, + "args": { + "External id": 1408669,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414810.362, "dur": 7.119, + "args": { + "External id": 1408670,"Record function id": 0, "Sequence number": 15108943, "Fwd thread id": 1, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414811.493, "dur": 3.428, + "args": { + "External id": 1408671,"Sequence number": 15108943, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1182 + } + }, + { + "ph": "f", "id": 123, "pid": 2338710, "tid": 2379450, "ts": 6410531414811.493, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531414812.750, "dur": 1.999, + "args": { + "External id": 1408672,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531414813.518, "dur": 1.110, + "args": { + "External id": 1408673,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414821.620, "dur": 12.062, + "args": { + "External id": 1408674,"Record function id": 0, "Sequence number": 15108942, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414822.658, "dur": 8.410, + "args": { + "External id": 1408675,"Sequence number": 15108942, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 1186 + } + }, + { + "ph": "f", "id": 124, "pid": 2338710, "tid": 2379450, "ts": 6410531414822.658, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531414826.556, "dur": 4.351, + "args": { + "External id": 1408676,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531414829.600, "dur": 1.188, + "args": { + "External id": 1408677,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414839.929, "dur": 200.285, + "args": { + "External id": 1408678,"Record function id": 0, "Sequence number": 15108941, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531414841.050, "dur": 188.884, + "args": { + "External id": 1408679,"Sequence number": 15108941, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1190 + } + }, + { + "ph": "f", "id": 125, "pid": 2338710, "tid": 2379450, "ts": 6410531414841.050, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531414846.343, "dur": 7.704, + "args": { + "External id": 1408680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531414849.059, "dur": 4.225, + "args": { + "External id": 1408681,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 1192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414850.994, "dur": 1.905, + "args": { + "External id": 1408682,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 1193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531414855.978, "dur": 87.817, + "args": { + "External id": 1408683,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 1194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531414945.296, "dur": 18.020, + "args": { + "External id": 1408684,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531414954.940, "dur": 7.392, + "args": { + "External id": 1408685,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 1196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414956.502, "dur": 5.572, + "args": { + "External id": 1408686,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 1197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531414965.742, "dur": 6.213, + "args": { + "External id": 1408687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531414967.523, "dur": 3.911, + "args": { + "External id": 1408688,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531414970.887, "dur": 0.457, + "args": { + "External id": 1408689,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531414972.779, "dur": 55.949, + "args": { + "External id": 1408690,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 1201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415046.680, "dur": 52.174, + "args": { + "External id": 1408691,"Record function id": 0, "Sequence number": 15108940, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415047.887, "dur": 7.047, + "args": { + "External id": 1408692,"Sequence number": 15108940, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1203 + } + }, + { + "ph": "f", "id": 126, "pid": 2338710, "tid": 2379450, "ts": 6410531415047.887, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531415049.782, "dur": 4.989, + "args": { + "External id": 1408693,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415053.165, "dur": 1.499, + "args": { + "External id": 1408694,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415106.494, "dur": 13.166, + "args": { + "External id": 1408695,"Record function id": 0, "Sequence number": 15108939, "Fwd thread id": 1, "Ev Idx": 1206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415108.269, "dur": 9.053, + "args": { + "External id": 1408696,"Sequence number": 15108939, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1207 + } + }, + { + "ph": "f", "id": 127, "pid": 2338710, "tid": 2379450, "ts": 6410531415108.269, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415109.649, "dur": 7.389, + "args": { + "External id": 1408697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415110.974, "dur": 5.153, + "args": { + "External id": 1408698,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415114.868, "dur": 1.108, + "args": { + "External id": 1408699,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531415126.993, "dur": 13.872, + "args": { + "External id": 1408700,"Record function id": 0, "Ev Idx": 1211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531415128.720, "dur": 11.222, + "args": { + "External id": 1408701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531415132.189, "dur": 7.247, + "args": { + "External id": 1408702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531415135.924, "dur": 3.364, + "args": { + "External id": 1408703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415144.574, "dur": 7.722, + "args": { + "External id": 1408704,"Record function id": 0, "Sequence number": 15108938, "Fwd thread id": 1, "Ev Idx": 1215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415146.169, "dur": 3.902, + "args": { + "External id": 1408705,"Sequence number": 15108938, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 1216 + } + }, + { + "ph": "f", "id": 128, "pid": 2338710, "tid": 2379450, "ts": 6410531415146.169, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531415147.598, "dur": 2.302, + "args": { + "External id": 1408706,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415148.509, "dur": 1.263, + "args": { + "External id": 1408707,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415156.068, "dur": 126.468, + "args": { + "External id": 1408708,"Record function id": 0, "Sequence number": 15108937, "Fwd thread id": 1, "Ev Idx": 1219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415157.079, "dur": 116.764, + "args": { + "External id": 1408709,"Sequence number": 15108937, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1220 + } + }, + { + "ph": "f", "id": 129, "pid": 2338710, "tid": 2379450, "ts": 6410531415157.079, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415161.187, "dur": 6.085, + "args": { + "External id": 1408710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415162.227, "dur": 4.537, + "args": { + "External id": 1408711,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 1222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415165.990, "dur": 0.653, + "args": { + "External id": 1408712,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 1223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531415168.318, "dur": 45.477, + "args": { + "External id": 1408713,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 1224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415215.364, "dur": 6.457, + "args": { + "External id": 1408714,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415216.290, "dur": 4.927, + "args": { + "External id": 1408715,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 1226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415219.943, "dur": 1.130, + "args": { + "External id": 1408716,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 1227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415223.639, "dur": 5.959, + "args": { + "External id": 1408717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415227.545, "dur": 1.419, + "args": { + "External id": 1408718,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415228.390, "dur": 0.495, + "args": { + "External id": 1408719,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531415230.236, "dur": 42.714, + "args": { + "External id": 1408720,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 1231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415288.175, "dur": 40.904, + "args": { + "External id": 1408721,"Record function id": 0, "Sequence number": 15108936, "Fwd thread id": 1, "Ev Idx": 1232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415289.282, "dur": 6.651, + "args": { + "External id": 1408722,"Sequence number": 15108936, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1233 + } + }, + { + "ph": "f", "id": 130, "pid": 2338710, "tid": 2379450, "ts": 6410531415289.282, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531415290.887, "dur": 4.887, + "args": { + "External id": 1408723,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415293.840, "dur": 1.774, + "args": { + "External id": 1408724,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531415299.530, "dur": 26.466, + "args": { + "External id": 1408725,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415333.531, "dur": 11.375, + "args": { + "External id": 1408726,"Record function id": 0, "Sequence number": 15108935, "Fwd thread id": 1, "Ev Idx": 1237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415336.773, "dur": 5.694, + "args": { + "External id": 1408727,"Sequence number": 15108935, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1238 + } + }, + { + "ph": "f", "id": 131, "pid": 2338710, "tid": 2379450, "ts": 6410531415336.773, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415338.229, "dur": 3.997, + "args": { + "External id": 1408728,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415339.345, "dur": 2.232, + "args": { + "External id": 1408729,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415340.877, "dur": 0.540, + "args": { + "External id": 1408730,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531415349.724, "dur": 10.004, + "args": { + "External id": 1408731,"Record function id": 0, "Ev Idx": 1242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531415351.628, "dur": 7.556, + "args": { + "External id": 1408732,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531415353.210, "dur": 5.528, + "args": { + "External id": 1408733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531415354.209, "dur": 4.359, + "args": { + "External id": 1408734,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415367.183, "dur": 12.267, + "args": { + "External id": 1408735,"Record function id": 0, "Sequence number": 15108934, "Fwd thread id": 1, "Ev Idx": 1246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415369.305, "dur": 8.168, + "args": { + "External id": 1408736,"Sequence number": 15108934, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1247 + } + }, + { + "ph": "f", "id": 132, "pid": 2338710, "tid": 2379450, "ts": 6410531415369.305, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531415372.801, "dur": 4.505, + "args": { + "External id": 1408737,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415375.990, "dur": 1.196, + "args": { + "External id": 1408738,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415383.139, "dur": 152.922, + "args": { + "External id": 1408739,"Record function id": 0, "Sequence number": 15108933, "Fwd thread id": 1, "Ev Idx": 1250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415384.231, "dur": 139.339, + "args": { + "External id": 1408740,"Sequence number": 15108933, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1251 + } + }, + { + "ph": "f", "id": 133, "pid": 2338710, "tid": 2379450, "ts": 6410531415384.231, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415388.237, "dur": 3.118, + "args": { + "External id": 1408741,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415388.953, "dur": 1.926, + "args": { + "External id": 1408742,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 1253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415389.950, "dur": 0.780, + "args": { + "External id": 1408743,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531415394.410, "dur": 65.600, + "args": { + "External id": 1408744,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 1255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415462.508, "dur": 5.294, + "args": { + "External id": 1408745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415463.589, "dur": 3.228, + "args": { + "External id": 1408746,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415465.454, "dur": 1.223, + "args": { + "External id": 1408747,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415469.294, "dur": 9.278, + "args": { + "External id": 1408748,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415471.299, "dur": 6.590, + "args": { + "External id": 1408749,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415476.650, "dur": 1.114, + "args": { + "External id": 1408750,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531415479.630, "dur": 43.147, + "args": { + "External id": 1408751,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 1262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415544.037, "dur": 31.488, + "args": { + "External id": 1408752,"Record function id": 0, "Sequence number": 15108932, "Fwd thread id": 1, "Ev Idx": 1263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415545.311, "dur": 4.793, + "args": { + "External id": 1408753,"Sequence number": 15108932, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1264 + } + }, + { + "ph": "f", "id": 134, "pid": 2338710, "tid": 2379450, "ts": 6410531415545.311, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531415547.323, "dur": 2.623, + "args": { + "External id": 1408754,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415548.386, "dur": 1.408, + "args": { + "External id": 1408755,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531415553.279, "dur": 19.289, + "args": { + "External id": 1408756,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415580.076, "dur": 16.424, + "args": { + "External id": 1408757,"Record function id": 0, "Sequence number": 15108931, "Fwd thread id": 1, "Ev Idx": 1268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531415581.629, "dur": 12.415, + "args": { + "External id": 1408758,"Sequence number": 15108931, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1269 + } + }, + { + "ph": "f", "id": 135, "pid": 2338710, "tid": 2379450, "ts": 6410531415581.629, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531415582.764, "dur": 11.040, + "args": { + "External id": 1408759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531415584.012, "dur": 9.155, + "args": { + "External id": 1408760,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415589.886, "dur": 3.148, + "args": { + "External id": 1408761,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531415601.237, "dur": 6.741, + "args": { + "External id": 1408762,"Record function id": 0, "Ev Idx": 1273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531415603.047, "dur": 4.330, + "args": { + "External id": 1408763,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531415604.770, "dur": 2.178, + "args": { + "External id": 1408764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531415605.412, "dur": 1.424, + "args": { + "External id": 1408765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531415615.650, "dur": 410.883, + "args": { + "External id": 1408766,"Record function id": 0, "Sequence number": 15108930, "Fwd thread id": 1, "Ev Idx": 1277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531415617.169, "dur": 375.138, + "args": { + "External id": 1408767,"Sequence number": 15108930, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1278 + } + }, + { + "ph": "f", "id": 136, "pid": 2338710, "tid": 2379450, "ts": 6410531415617.169, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531415659.865, "dur": 2.480, + "args": { + "External id": 1408768,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415660.865, "dur": 1.300, + "args": { + "External id": 1408769,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531415682.362, "dur": 5.188, + "args": { + "External id": 1408770,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531415698.446, "dur": 2.534, + "args": { + "External id": 1408771,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415870.715, "dur": 1.746, + "args": { + "External id": 1408772,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 1283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531415877.033, "dur": 39.634, + "args": { + "External id": 1408773,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 1284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415889.747, "dur": 1.317, + "args": { + "External id": 1408774,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 1285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531415923.428, "dur": 38.491, + "args": { + "External id": 1408775,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 1286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531415925.849, "dur": 35.790, + "args": { + "External id": 1408776,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 1287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531415933.413, "dur": 7.237, + "args": { + "External id": 1408777,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531415942.798, "dur": 18.134, + "args": { + "External id": 1408778,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 1289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531415969.677, "dur": 5.195, + "args": { + "External id": 1408779,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 1290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415970.910, "dur": 3.844, + "args": { + "External id": 1408780,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 1291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531415982.086, "dur": 2.465, + "args": { + "External id": 1408781,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531415983.118, "dur": 1.321, + "args": { + "External id": 1408782,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531416003.613, "dur": 18.876, + "args": { + "External id": 1408783,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531416037.314, "dur": 13.636, + "args": { + "External id": 1408784,"Record function id": 0, "Ev Idx": 1295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531416042.220, "dur": 8.038, + "args": { + "External id": 1408785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531416044.042, "dur": 5.191, + "args": { + "External id": 1408786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531416047.357, "dur": 1.742, + "args": { + "External id": 1408787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416055.161, "dur": 49.673, + "args": { + "External id": 1408788,"Record function id": 0, "Sequence number": 15108929, "Fwd thread id": 1, "Ev Idx": 1299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416098.049, "dur": 1.992, + "args": { + "External id": 1408789,"Sequence number": 15108929, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1300 + } + }, + { + "ph": "f", "id": 137, "pid": 2338710, "tid": 2379450, "ts": 6410531416098.049, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531416111.650, "dur": 527.603, + "args": { + "External id": 1408790,"Record function id": 0, "Sequence number": 15108928, "Fwd thread id": 1, "Ev Idx": 1301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531416112.928, "dur": 511.481, + "args": { + "External id": 1408791,"Sequence number": 15108928, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1302 + } + }, + { + "ph": "f", "id": 138, "pid": 2338710, "tid": 2379450, "ts": 6410531416112.928, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531416152.024, "dur": 9.963, + "args": { + "External id": 1408792,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531416157.366, "dur": 4.258, + "args": { + "External id": 1408793,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 1304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416165.587, "dur": 10.350, + "args": { + "External id": 1408794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416169.965, "dur": 5.198, + "args": { + "External id": 1408795,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416174.056, "dur": 0.928, + "args": { + "External id": 1408796,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2379450, + "ts": 6410531416180.258, "dur": 108.891, + "args": { + "External id": 1408797,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 1308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416181.614, "dur": 3.209, + "args": { + "External id": 1408798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 1309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416182.413, "dur": 1.894, + "args": { + "External id": 1408799,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416183.398, "dur": 0.817, + "args": { + "External id": 1408800,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2379450, + "ts": 6410531416189.023, "dur": 99.485, + "args": { + "External id": 1408801,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 1312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531416191.057, "dur": 96.402, + "args": { + "External id": 1408802,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531416294.125, "dur": 3.469, + "args": { + "External id": 1408803,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 1314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531416295.913, "dur": 1.505, + "args": { + "External id": 1408804,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 1315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531416337.245, "dur": 4.126, + "args": { + "External id": 1408805,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531416345.113, "dur": 7.339, + "args": { + "External id": 1408806,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531416353.555, "dur": 2.606, + "args": { + "External id": 1408807,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531416396.370, "dur": 2.653, + "args": { + "External id": 1408808,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531416397.474, "dur": 1.365, + "args": { + "External id": 1408809,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338710, "tid": 2379450, + "ts": 6410531416441.940, "dur": 159.366, + "args": { + "External id": 1408810,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410531416448.105, "dur": 9.207, + "args": { + "External id": 1408811,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416454.765, "dur": 1.193, + "args": { + "External id": 1408812,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531416458.739, "dur": 9.731, + "args": { + "External id": 1408813,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 1324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416466.810, "dur": 0.676, + "args": { + "External id": 1408814,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 1325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410531416470.505, "dur": 1.791, + "args": { + "External id": 1408815,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 1326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416471.352, "dur": 0.567, + "args": { + "External id": 1408816,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531416475.031, "dur": 2.541, + "args": { + "External id": 1408817,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 1328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416475.894, "dur": 0.785, + "args": { + "External id": 1408818,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 1329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531416486.765, "dur": 2.325, + "args": { + "External id": 1408819,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 1330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416488.054, "dur": 0.700, + "args": { + "External id": 1408820,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 1331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531416490.000, "dur": 11.467, + "args": { + "External id": 1408821,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 1332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531416496.219, "dur": 5.053, + "args": { + "External id": 1408822,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 1333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531416502.348, "dur": 4.817, + "args": { + "External id": 1408823,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416506.159, "dur": 0.715, + "args": { + "External id": 1408824,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 1335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531416507.999, "dur": 4.479, + "args": { + "External id": 1408825,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 1336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531416508.665, "dur": 3.708, + "args": { + "External id": 1408826,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 1337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531416514.024, "dur": 67.813, + "args": { + "External id": 1408827,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531416586.552, "dur": 1.619, + "args": { + "External id": 1408828,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 1339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410531416591.298, "dur": 5.083, + "args": { + "External id": 1408829,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 1340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416594.996, "dur": 0.604, + "args": { + "External id": 1408830,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 1341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531416599.010, "dur": 1.102, + "args": { + "External id": 1408831,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 1342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531416652.884, "dur": 15.370, + "args": { + "External id": 1408832,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531416655.362, "dur": 11.819, + "args": { + "External id": 1408833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531416657.802, "dur": 8.177, + "args": { + "External id": 1408834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531416663.482, "dur": 2.379, + "args": { + "External id": 1408835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416672.522, "dur": 10.661, + "args": { + "External id": 1408836,"Record function id": 0, "Sequence number": 15108927, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416673.736, "dur": 6.902, + "args": { + "External id": 1408837,"Sequence number": 15108927, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 1348 + } + }, + { + "ph": "f", "id": 139, "pid": 2338710, "tid": 2379450, "ts": 6410531416673.736, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531416677.794, "dur": 2.616, + "args": { + "External id": 1408838,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531416678.906, "dur": 1.386, + "args": { + "External id": 1408839,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416687.116, "dur": 132.096, + "args": { + "External id": 1408840,"Record function id": 0, "Sequence number": 15108926, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416688.392, "dur": 122.823, + "args": { + "External id": 1408841,"Sequence number": 15108926, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1352 + } + }, + { + "ph": "f", "id": 140, "pid": 2338710, "tid": 2379450, "ts": 6410531416688.392, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416692.783, "dur": 8.729, + "args": { + "External id": 1408842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416694.310, "dur": 6.569, + "args": { + "External id": 1408843,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 1354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416698.112, "dur": 2.599, + "args": { + "External id": 1408844,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531416702.625, "dur": 50.308, + "args": { + "External id": 1408845,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 1356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416754.573, "dur": 6.941, + "args": { + "External id": 1408846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416755.765, "dur": 4.900, + "args": { + "External id": 1408847,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416759.599, "dur": 0.895, + "args": { + "External id": 1408848,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416763.444, "dur": 6.184, + "args": { + "External id": 1408849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416765.070, "dur": 4.029, + "args": { + "External id": 1408850,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416768.351, "dur": 0.612, + "args": { + "External id": 1408851,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531416770.204, "dur": 39.779, + "args": { + "External id": 1408852,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 1363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416825.182, "dur": 10.470, + "args": { + "External id": 1408853,"Record function id": 0, "Sequence number": 15108925, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416826.520, "dur": 7.592, + "args": { + "External id": 1408854,"Sequence number": 15108925, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1365 + } + }, + { + "ph": "f", "id": 141, "pid": 2338710, "tid": 2379450, "ts": 6410531416826.520, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531416828.425, "dur": 5.465, + "args": { + "External id": 1408855,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531416832.299, "dur": 1.471, + "args": { + "External id": 1408856,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416839.739, "dur": 11.619, + "args": { + "External id": 1408857,"Record function id": 0, "Sequence number": 15108924, "Fwd thread id": 1, "Ev Idx": 1368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416840.850, "dur": 7.311, + "args": { + "External id": 1408858,"Sequence number": 15108924, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1369 + } + }, + { + "ph": "f", "id": 142, "pid": 2338710, "tid": 2379450, "ts": 6410531416840.850, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416842.029, "dur": 5.858, + "args": { + "External id": 1408859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416843.221, "dur": 4.147, + "args": { + "External id": 1408860,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416846.590, "dur": 0.604, + "args": { + "External id": 1408861,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531416855.659, "dur": 9.063, + "args": { + "External id": 1408862,"Record function id": 0, "Ev Idx": 1373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531416857.399, "dur": 6.714, + "args": { + "External id": 1408863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531416858.826, "dur": 4.860, + "args": { + "External id": 1408864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531416859.693, "dur": 3.871, + "args": { + "External id": 1408865,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416868.525, "dur": 11.048, + "args": { + "External id": 1408866,"Record function id": 0, "Sequence number": 15108923, "Fwd thread id": 1, "Ev Idx": 1377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416869.533, "dur": 6.167, + "args": { + "External id": 1408867,"Sequence number": 15108923, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 1378 + } + }, + { + "ph": "f", "id": 143, "pid": 2338710, "tid": 2379450, "ts": 6410531416869.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531416873.455, "dur": 2.063, + "args": { + "External id": 1408868,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531416874.242, "dur": 1.111, + "args": { + "External id": 1408869,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416883.276, "dur": 114.015, + "args": { + "External id": 1408870,"Record function id": 0, "Sequence number": 15108922, "Fwd thread id": 1, "Ev Idx": 1381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531416886.642, "dur": 100.898, + "args": { + "External id": 1408871,"Sequence number": 15108922, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1382 + } + }, + { + "ph": "f", "id": 144, "pid": 2338710, "tid": 2379450, "ts": 6410531416886.642, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416890.123, "dur": 3.216, + "args": { + "External id": 1408872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416891.273, "dur": 1.572, + "args": { + "External id": 1408873,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 1384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416892.065, "dur": 0.660, + "args": { + "External id": 1408874,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531416894.106, "dur": 38.096, + "args": { + "External id": 1408875,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 1386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416933.628, "dur": 6.324, + "args": { + "External id": 1408876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416934.580, "dur": 4.645, + "args": { + "External id": 1408877,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416938.400, "dur": 0.686, + "args": { + "External id": 1408878,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531416941.370, "dur": 5.856, + "args": { + "External id": 1408879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531416942.733, "dur": 3.827, + "args": { + "External id": 1408880,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531416946.030, "dur": 0.398, + "args": { + "External id": 1408881,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531416947.734, "dur": 38.954, + "args": { + "External id": 1408882,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 1393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417005.612, "dur": 42.553, + "args": { + "External id": 1408883,"Record function id": 0, "Sequence number": 15108921, "Fwd thread id": 1, "Ev Idx": 1394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417006.787, "dur": 7.467, + "args": { + "External id": 1408884,"Sequence number": 15108921, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1395 + } + }, + { + "ph": "f", "id": 145, "pid": 2338710, "tid": 2379450, "ts": 6410531417006.787, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531417011.740, "dur": 2.314, + "args": { + "External id": 1408885,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417012.866, "dur": 1.067, + "args": { + "External id": 1408886,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531417017.664, "dur": 26.630, + "args": { + "External id": 1408887,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417052.793, "dur": 52.659, + "args": { + "External id": 1408888,"Record function id": 0, "Sequence number": 15108920, "Fwd thread id": 1, "Ev Idx": 1399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417054.234, "dur": 47.774, + "args": { + "External id": 1408889,"Sequence number": 15108920, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1400 + } + }, + { + "ph": "f", "id": 146, "pid": 2338710, "tid": 2379450, "ts": 6410531417054.234, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531417092.708, "dur": 9.008, + "args": { + "External id": 1408890,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531417095.125, "dur": 5.757, + "args": { + "External id": 1408891,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417099.747, "dur": 0.786, + "args": { + "External id": 1408892,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531417112.594, "dur": 10.264, + "args": { + "External id": 1408893,"Record function id": 0, "Ev Idx": 1404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531417114.300, "dur": 7.952, + "args": { + "External id": 1408894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531417115.979, "dur": 5.728, + "args": { + "External id": 1408895,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531417119.365, "dur": 2.169, + "args": { + "External id": 1408896,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531417128.016, "dur": 506.759, + "args": { + "External id": 1408897,"Record function id": 0, "Sequence number": 15108919, "Fwd thread id": 1, "Ev Idx": 1408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531417129.496, "dur": 462.731, + "args": { + "External id": 1408898,"Sequence number": 15108919, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 1409 + } + }, + { + "ph": "f", "id": 147, "pid": 2338710, "tid": 2379450, "ts": 6410531417129.496, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2379450, + "ts": 6410531417156.927, "dur": 42.212, + "args": { + "External id": 1408899,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531417158.649, "dur": 40.243, + "args": { + "External id": 1408900,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531417161.884, "dur": 7.701, + "args": { + "External id": 1408901,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 1412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531417164.691, "dur": 4.276, + "args": { + "External id": 1408902,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531417171.290, "dur": 27.142, + "args": { + "External id": 1408903,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531417215.080, "dur": 3.057, + "args": { + "External id": 1408904,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417216.231, "dur": 1.725, + "args": { + "External id": 1408905,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531417224.963, "dur": 1.767, + "args": { + "External id": 1408906,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417225.676, "dur": 0.930, + "args": { + "External id": 1408907,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531417240.725, "dur": 2.849, + "args": { + "External id": 1408908,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531417256.170, "dur": 3.077, + "args": { + "External id": 1408909,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417459.436, "dur": 6.152, + "args": { + "External id": 1408910,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 1421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531417472.859, "dur": 40.175, + "args": { + "External id": 1408911,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 1422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417487.140, "dur": 0.980, + "args": { + "External id": 1408912,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 1423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531417520.271, "dur": 32.536, + "args": { + "External id": 1408913,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 1424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531417522.304, "dur": 30.265, + "args": { + "External id": 1408914,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 1425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417529.552, "dur": 4.369, + "args": { + "External id": 1408915,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531417535.586, "dur": 16.467, + "args": { + "External id": 1408916,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 1427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531417557.603, "dur": 3.010, + "args": { + "External id": 1408917,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 1428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417559.021, "dur": 1.459, + "args": { + "External id": 1408918,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 1429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531417571.488, "dur": 2.740, + "args": { + "External id": 1408919,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417572.691, "dur": 1.375, + "args": { + "External id": 1408920,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531417576.823, "dur": 4.619, + "args": { + "External id": 1408921,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417579.993, "dur": 1.340, + "args": { + "External id": 1408922,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531417613.054, "dur": 19.883, + "args": { + "External id": 1408923,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531417648.937, "dur": 9.819, + "args": { + "External id": 1408924,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531417651.236, "dur": 6.669, + "args": { + "External id": 1408925,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531417654.025, "dur": 2.885, + "args": { + "External id": 1408926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531417654.995, "dur": 1.759, + "args": { + "External id": 1408927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417662.819, "dur": 12.639, + "args": { + "External id": 1408928,"Record function id": 0, "Sequence number": 15108918, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417663.970, "dur": 7.686, + "args": { + "External id": 1408929,"Sequence number": 15108918, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1440 + } + }, + { + "ph": "f", "id": 148, "pid": 2338710, "tid": 2379450, "ts": 6410531417663.970, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531417668.734, "dur": 2.655, + "args": { + "External id": 1408930,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417669.768, "dur": 1.478, + "args": { + "External id": 1408931,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417679.563, "dur": 164.957, + "args": { + "External id": 1408932,"Record function id": 0, "Sequence number": 15108917, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417681.169, "dur": 155.180, + "args": { + "External id": 1408933,"Sequence number": 15108917, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1444 + } + }, + { + "ph": "f", "id": 149, "pid": 2338710, "tid": 2379450, "ts": 6410531417681.169, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531417685.901, "dur": 7.680, + "args": { + "External id": 1408934,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531417687.611, "dur": 5.289, + "args": { + "External id": 1408935,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 1446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417691.646, "dur": 1.027, + "args": { + "External id": 1408936,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531417694.863, "dur": 79.055, + "args": { + "External id": 1408937,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 1448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531417775.497, "dur": 6.815, + "args": { + "External id": 1408938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531417776.070, "dur": 5.560, + "args": { + "External id": 1408939,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417780.348, "dur": 1.101, + "args": { + "External id": 1408940,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531417784.341, "dur": 9.294, + "args": { + "External id": 1408941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531417785.742, "dur": 7.148, + "args": { + "External id": 1408942,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417789.436, "dur": 3.301, + "args": { + "External id": 1408943,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531417794.530, "dur": 40.789, + "args": { + "External id": 1408944,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 1455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417849.928, "dur": 11.740, + "args": { + "External id": 1408945,"Record function id": 0, "Sequence number": 15108916, "Fwd thread id": 1, "Ev Idx": 1456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417851.012, "dur": 7.383, + "args": { + "External id": 1408946,"Sequence number": 15108916, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1457 + } + }, + { + "ph": "f", "id": 150, "pid": 2338710, "tid": 2379450, "ts": 6410531417851.012, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531417852.755, "dur": 5.466, + "args": { + "External id": 1408947,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417856.541, "dur": 1.520, + "args": { + "External id": 1408948,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417868.121, "dur": 10.797, + "args": { + "External id": 1408949,"Record function id": 0, "Sequence number": 15108915, "Fwd thread id": 1, "Ev Idx": 1460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417869.373, "dur": 7.562, + "args": { + "External id": 1408950,"Sequence number": 15108915, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1461 + } + }, + { + "ph": "f", "id": 151, "pid": 2338710, "tid": 2379450, "ts": 6410531417869.373, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531417870.241, "dur": 6.413, + "args": { + "External id": 1408951,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531417874.061, "dur": 2.023, + "args": { + "External id": 1408952,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417875.227, "dur": 0.755, + "args": { + "External id": 1408953,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531417883.535, "dur": 6.754, + "args": { + "External id": 1408954,"Record function id": 0, "Ev Idx": 1465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531417884.833, "dur": 4.875, + "args": { + "External id": 1408955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531417886.476, "dur": 2.786, + "args": { + "External id": 1408956,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531417887.382, "dur": 1.710, + "args": { + "External id": 1408957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417893.944, "dur": 7.141, + "args": { + "External id": 1408958,"Record function id": 0, "Sequence number": 15108914, "Fwd thread id": 1, "Ev Idx": 1469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531417895.128, "dur": 3.750, + "args": { + "External id": 1408959,"Sequence number": 15108914, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1470 + } + }, + { + "ph": "f", "id": 152, "pid": 2338710, "tid": 2379450, "ts": 6410531417895.128, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531417896.648, "dur": 2.069, + "args": { + "External id": 1408960,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531417897.280, "dur": 1.308, + "args": { + "External id": 1408961,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531417908.165, "dur": 460.525, + "args": { + "External id": 1408962,"Record function id": 0, "Sequence number": 15108913, "Fwd thread id": 1, "Ev Idx": 1473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531417909.515, "dur": 430.487, + "args": { + "External id": 1408963,"Sequence number": 15108913, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1474 + } + }, + { + "ph": "f", "id": 153, "pid": 2338710, "tid": 2379450, "ts": 6410531417909.515, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531417927.387, "dur": 6.353, + "args": { + "External id": 1408964,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417929.662, "dur": 3.565, + "args": { + "External id": 1408965,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531417936.085, "dur": 6.504, + "args": { + "External id": 1408966,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417939.971, "dur": 2.387, + "args": { + "External id": 1408967,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531417944.339, "dur": 5.596, + "args": { + "External id": 1408968,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531417945.420, "dur": 4.280, + "args": { + "External id": 1408969,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531417982.784, "dur": 326.132, + "args": { + "External id": 1408970,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531418118.995, "dur": 7.937, + "args": { + "External id": 1408971,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531418128.949, "dur": 4.943, + "args": { + "External id": 1408972,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531418134.951, "dur": 2.289, + "args": { + "External id": 1408973,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531418138.088, "dur": 2.227, + "args": { + "External id": 1408974,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531418190.102, "dur": 5.387, + "args": { + "External id": 1408975,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531418193.464, "dur": 1.866, + "args": { + "External id": 1408976,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531418199.805, "dur": 33.624, + "args": { + "External id": 1408977,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531418207.249, "dur": 1.213, + "args": { + "External id": 1408978,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531418234.951, "dur": 1.445, + "args": { + "External id": 1408979,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531418235.587, "dur": 0.723, + "args": { + "External id": 1408980,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531418237.153, "dur": 18.945, + "args": { + "External id": 1408981,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531418238.809, "dur": 3.036, + "args": { + "External id": 1408982,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531418324.701, "dur": 4.370, + "args": { + "External id": 1408983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531418332.481, "dur": 0.995, + "args": { + "External id": 1408984,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410531418335.946, "dur": 0.592, + "args": { + "External id": 1408985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531418380.725, "dur": 309.720, + "args": { + "External id": 1408986,"Record function id": 0, "Sequence number": 15108912, "Fwd thread id": 1, "Ev Idx": 1497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531418382.935, "dur": 297.608, + "args": { + "External id": 1408987,"Sequence number": 15108912, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1498 + } + }, + { + "ph": "f", "id": 154, "pid": 2338710, "tid": 2379450, "ts": 6410531418382.935, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531418410.022, "dur": 80.008, + "args": { + "External id": 1408988,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531418433.908, "dur": 7.820, + "args": { + "External id": 1408989,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531418443.736, "dur": 45.653, + "args": { + "External id": 1408990,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 1501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531418503.208, "dur": 4.980, + "args": { + "External id": 1408991,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531418504.980, "dur": 2.844, + "args": { + "External id": 1408992,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531418701.498, "dur": 198.531, + "args": { + "External id": 1408993,"Record function id": 0, "Sequence number": 15108911, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531418703.523, "dur": 188.383, + "args": { + "External id": 1408994,"Sequence number": 15108911, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1505 + } + }, + { + "ph": "f", "id": 155, "pid": 2338710, "tid": 2379450, "ts": 6410531418703.523, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410531418724.744, "dur": 50.122, + "args": { + "External id": 1408995,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531418729.836, "dur": 3.513, + "args": { + "External id": 1408996,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531418734.402, "dur": 39.835, + "args": { + "External id": 1408997,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 1508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410531418783.317, "dur": 7.404, + "args": { + "External id": 1408998,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531418784.856, "dur": 5.518, + "args": { + "External id": 1408999,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418907.652, "dur": 22.474, + "args": { + "External id": 1409000,"Record function id": 0, "Sequence number": 15108910, "Fwd thread id": 1, "Ev Idx": 1511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418909.499, "dur": 16.034, + "args": { + "External id": 1409001,"Sequence number": 15108910, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1512 + } + }, + { + "ph": "f", "id": 156, "pid": 2338710, "tid": 2379450, "ts": 6410531418909.499, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531418912.388, "dur": 12.856, + "args": { + "External id": 1409002,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531418918.716, "dur": 6.333, + "args": { + "External id": 1409003,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418936.760, "dur": 7.952, + "args": { + "External id": 1409004,"Record function id": 0, "Sequence number": 15108909, "Fwd thread id": 1, "Ev Idx": 1515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418938.027, "dur": 3.917, + "args": { + "External id": 1409005,"Sequence number": 15108909, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1516 + } + }, + { + "ph": "f", "id": 157, "pid": 2338710, "tid": 2379450, "ts": 6410531418938.027, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531418939.520, "dur": 2.255, + "args": { + "External id": 1409006,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531418940.442, "dur": 1.128, + "args": { + "External id": 1409007,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418948.694, "dur": 9.825, + "args": { + "External id": 1409008,"Record function id": 0, "Sequence number": 15108908, "Fwd thread id": 1, "Ev Idx": 1519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418949.801, "dur": 5.534, + "args": { + "External id": 1409009,"Sequence number": 15108908, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1520 + } + }, + { + "ph": "f", "id": 158, "pid": 2338710, "tid": 2379450, "ts": 6410531418949.801, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531418951.015, "dur": 4.162, + "args": { + "External id": 1409010,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531418954.050, "dur": 0.972, + "args": { + "External id": 1409011,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418962.348, "dur": 10.101, + "args": { + "External id": 1409012,"Record function id": 0, "Sequence number": 15108907, "Fwd thread id": 1, "Ev Idx": 1523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418963.471, "dur": 6.262, + "args": { + "External id": 1409013,"Sequence number": 15108907, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 1524 + } + }, + { + "ph": "f", "id": 159, "pid": 2338710, "tid": 2379450, "ts": 6410531418963.471, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531418965.023, "dur": 4.544, + "args": { + "External id": 1409014,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531418968.117, "dur": 1.341, + "args": { + "External id": 1409015,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418976.395, "dur": 274.889, + "args": { + "External id": 1409016,"Record function id": 0, "Sequence number": 15108906, "Fwd thread id": 1, "Ev Idx": 1527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531418977.592, "dur": 260.819, + "args": { + "External id": 1409017,"Sequence number": 15108906, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1528 + } + }, + { + "ph": "f", "id": 160, "pid": 2338710, "tid": 2379450, "ts": 6410531418977.592, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531418982.238, "dur": 9.301, + "args": { + "External id": 1409018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531418984.605, "dur": 6.130, + "args": { + "External id": 1409019,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531418986.213, "dur": 4.243, + "args": { + "External id": 1409020,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 1531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531418996.310, "dur": 128.786, + "args": { + "External id": 1409021,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 1532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419128.340, "dur": 8.691, + "args": { + "External id": 1409022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419129.780, "dur": 5.926, + "args": { + "External id": 1409023,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 1534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419134.088, "dur": 1.422, + "args": { + "External id": 1409024,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419165.697, "dur": 6.502, + "args": { + "External id": 1409025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419167.515, "dur": 3.996, + "args": { + "External id": 1409026,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419170.646, "dur": 0.749, + "args": { + "External id": 1409027,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531419173.267, "dur": 63.836, + "args": { + "External id": 1409028,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 1539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419261.045, "dur": 11.454, + "args": { + "External id": 1409029,"Record function id": 0, "Sequence number": 15108905, "Fwd thread id": 1, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419262.293, "dur": 7.537, + "args": { + "External id": 1409030,"Sequence number": 15108905, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1541 + } + }, + { + "ph": "f", "id": 161, "pid": 2338710, "tid": 2379450, "ts": 6410531419262.293, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531419264.222, "dur": 5.441, + "args": { + "External id": 1409031,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531419267.737, "dur": 1.778, + "args": { + "External id": 1409032,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419276.495, "dur": 11.525, + "args": { + "External id": 1409033,"Record function id": 0, "Sequence number": 15108904, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419277.464, "dur": 7.581, + "args": { + "External id": 1409034,"Sequence number": 15108904, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1545 + } + }, + { + "ph": "f", "id": 162, "pid": 2338710, "tid": 2379450, "ts": 6410531419277.464, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419278.453, "dur": 6.314, + "args": { + "External id": 1409035,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419282.156, "dur": 2.039, + "args": { + "External id": 1409036,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419283.126, "dur": 0.919, + "args": { + "External id": 1409037,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531419294.958, "dur": 13.226, + "args": { + "External id": 1409038,"Record function id": 0, "Ev Idx": 1549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531419296.483, "dur": 10.882, + "args": { + "External id": 1409039,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531419299.562, "dur": 7.249, + "args": { + "External id": 1409040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531419300.958, "dur": 5.746, + "args": { + "External id": 1409041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419311.954, "dur": 8.412, + "args": { + "External id": 1409042,"Record function id": 0, "Sequence number": 15108903, "Fwd thread id": 1, "Ev Idx": 1553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419313.020, "dur": 5.041, + "args": { + "External id": 1409043,"Sequence number": 15108903, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 1554 + } + }, + { + "ph": "f", "id": 163, "pid": 2338710, "tid": 2379450, "ts": 6410531419313.020, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531419316.330, "dur": 1.581, + "args": { + "External id": 1409044,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531419316.762, "dur": 0.998, + "args": { + "External id": 1409045,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419326.842, "dur": 140.200, + "args": { + "External id": 1409046,"Record function id": 0, "Sequence number": 15108902, "Fwd thread id": 1, "Ev Idx": 1557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419328.069, "dur": 127.547, + "args": { + "External id": 1409047,"Sequence number": 15108902, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1558 + } + }, + { + "ph": "f", "id": 164, "pid": 2338710, "tid": 2379450, "ts": 6410531419328.069, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419332.036, "dur": 7.164, + "args": { + "External id": 1409048,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419332.622, "dur": 6.027, + "args": { + "External id": 1409049,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 1560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419337.924, "dur": 0.589, + "args": { + "External id": 1409050,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531419340.191, "dur": 34.227, + "args": { + "External id": 1409051,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 1562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419378.090, "dur": 4.960, + "args": { + "External id": 1409052,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419378.795, "dur": 3.529, + "args": { + "External id": 1409053,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 1564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419379.725, "dur": 2.398, + "args": { + "External id": 1409054,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 1565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419384.543, "dur": 6.228, + "args": { + "External id": 1409055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419385.684, "dur": 4.534, + "args": { + "External id": 1409056,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419389.589, "dur": 0.471, + "args": { + "External id": 1409057,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531419396.521, "dur": 57.677, + "args": { + "External id": 1409058,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 1569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419477.325, "dur": 44.349, + "args": { + "External id": 1409059,"Record function id": 0, "Sequence number": 15108901, "Fwd thread id": 1, "Ev Idx": 1570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419478.445, "dur": 5.116, + "args": { + "External id": 1409060,"Sequence number": 15108901, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1571 + } + }, + { + "ph": "f", "id": 165, "pid": 2338710, "tid": 2379450, "ts": 6410531419478.445, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531419480.679, "dur": 2.727, + "args": { + "External id": 1409061,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531419481.364, "dur": 1.862, + "args": { + "External id": 1409062,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410531419487.318, "dur": 30.767, + "args": { + "External id": 1409063,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419529.021, "dur": 11.555, + "args": { + "External id": 1409064,"Record function id": 0, "Sequence number": 15108900, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419529.980, "dur": 7.944, + "args": { + "External id": 1409065,"Sequence number": 15108900, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1576 + } + }, + { + "ph": "f", "id": 166, "pid": 2338710, "tid": 2379450, "ts": 6410531419529.980, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419531.329, "dur": 6.314, + "args": { + "External id": 1409066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419532.358, "dur": 4.524, + "args": { + "External id": 1409067,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419536.112, "dur": 0.573, + "args": { + "External id": 1409068,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531419545.644, "dur": 9.441, + "args": { + "External id": 1409069,"Record function id": 0, "Ev Idx": 1580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531419547.258, "dur": 7.168, + "args": { + "External id": 1409070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531419548.826, "dur": 5.033, + "args": { + "External id": 1409071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531419552.131, "dur": 1.561, + "args": { + "External id": 1409072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419558.891, "dur": 7.154, + "args": { + "External id": 1409073,"Record function id": 0, "Sequence number": 15108899, "Fwd thread id": 1, "Ev Idx": 1584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419560.184, "dur": 3.269, + "args": { + "External id": 1409074,"Sequence number": 15108899, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1585 + } + }, + { + "ph": "f", "id": 167, "pid": 2338710, "tid": 2379450, "ts": 6410531419560.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531419561.298, "dur": 1.981, + "args": { + "External id": 1409075,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531419561.954, "dur": 1.207, + "args": { + "External id": 1409076,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419570.045, "dur": 120.131, + "args": { + "External id": 1409077,"Record function id": 0, "Sequence number": 15108898, "Fwd thread id": 1, "Ev Idx": 1588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419570.867, "dur": 109.986, + "args": { + "External id": 1409078,"Sequence number": 15108898, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1589 + } + }, + { + "ph": "f", "id": 168, "pid": 2338710, "tid": 2379450, "ts": 6410531419570.867, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419574.034, "dur": 5.333, + "args": { + "External id": 1409079,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419577.167, "dur": 1.697, + "args": { + "External id": 1409080,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 1591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419577.958, "dur": 0.780, + "args": { + "External id": 1409081,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531419580.291, "dur": 46.004, + "args": { + "External id": 1409082,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419627.665, "dur": 6.090, + "args": { + "External id": 1409083,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419628.403, "dur": 4.619, + "args": { + "External id": 1409084,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419632.021, "dur": 0.854, + "args": { + "External id": 1409085,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419637.665, "dur": 3.190, + "args": { + "External id": 1409086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419638.925, "dur": 1.340, + "args": { + "External id": 1409087,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419639.582, "dur": 0.579, + "args": { + "External id": 1409088,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531419641.351, "dur": 38.724, + "args": { + "External id": 1409089,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419696.015, "dur": 33.538, + "args": { + "External id": 1409090,"Record function id": 0, "Sequence number": 15108897, "Fwd thread id": 1, "Ev Idx": 1601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419697.050, "dur": 9.437, + "args": { + "External id": 1409091,"Sequence number": 15108897, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1602 + } + }, + { + "ph": "f", "id": 169, "pid": 2338710, "tid": 2379450, "ts": 6410531419697.050, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531419701.403, "dur": 4.928, + "args": { + "External id": 1409092,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531419704.709, "dur": 1.442, + "args": { + "External id": 1409093,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531419709.314, "dur": 16.734, + "args": { + "External id": 1409094,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419733.907, "dur": 7.342, + "args": { + "External id": 1409095,"Record function id": 0, "Sequence number": 15108896, "Fwd thread id": 1, "Ev Idx": 1606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410531419734.887, "dur": 4.385, + "args": { + "External id": 1409096,"Sequence number": 15108896, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1607 + } + }, + { + "ph": "f", "id": 170, "pid": 2338710, "tid": 2379450, "ts": 6410531419734.887, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410531419735.869, "dur": 3.151, + "args": { + "External id": 1409097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410531419736.579, "dur": 1.812, + "args": { + "External id": 1409098,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531419737.704, "dur": 0.516, + "args": { + "External id": 1409099,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531419745.678, "dur": 5.330, + "args": { + "External id": 1409100,"Record function id": 0, "Ev Idx": 1611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531419747.044, "dur": 3.447, + "args": { + "External id": 1409101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531419748.092, "dur": 1.777, + "args": { + "External id": 1409102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531419748.647, "dur": 1.083, + "args": { + "External id": 1409103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531419755.549, "dur": 481.836, + "args": { + "External id": 1409104,"Record function id": 0, "Sequence number": 15108895, "Fwd thread id": 1, "Ev Idx": 1615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531419756.697, "dur": 436.964, + "args": { + "External id": 1409105,"Sequence number": 15108895, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1616 + } + }, + { + "ph": "f", "id": 171, "pid": 2338710, "tid": 2379450, "ts": 6410531419756.697, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531419803.728, "dur": 1.770, + "args": { + "External id": 1409106,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531419804.294, "dur": 1.038, + "args": { + "External id": 1409107,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531419822.666, "dur": 4.153, + "args": { + "External id": 1409108,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531419838.090, "dur": 2.367, + "args": { + "External id": 1409109,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531420013.730, "dur": 2.095, + "args": { + "External id": 1409110,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 1621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531420020.811, "dur": 89.168, + "args": { + "External id": 1409111,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 1622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420042.661, "dur": 1.090, + "args": { + "External id": 1409112,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 1623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531420119.739, "dur": 39.540, + "args": { + "External id": 1409113,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 1624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531420124.312, "dur": 34.703, + "args": { + "External id": 1409114,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 1625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420129.256, "dur": 4.977, + "args": { + "External id": 1409115,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531420136.351, "dur": 22.049, + "args": { + "External id": 1409116,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 1627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410531420165.339, "dur": 3.518, + "args": { + "External id": 1409117,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 1628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531420166.759, "dur": 1.979, + "args": { + "External id": 1409118,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 1629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531420179.769, "dur": 4.583, + "args": { + "External id": 1409119,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531420183.095, "dur": 1.124, + "args": { + "External id": 1409120,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410531420211.096, "dur": 19.643, + "args": { + "External id": 1409121,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531420252.475, "dur": 10.125, + "args": { + "External id": 1409122,"Record function id": 0, "Ev Idx": 1633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531420254.919, "dur": 6.699, + "args": { + "External id": 1409123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531420257.586, "dur": 2.985, + "args": { + "External id": 1409124,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531420258.611, "dur": 1.862, + "args": { + "External id": 1409125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531420267.601, "dur": 3321.299, + "args": { + "External id": 1409126,"Record function id": 0, "Ev Idx": 1637 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 2338710, "tid": 2379450, + "ts": 6410531420305.691, "dur": 1172.896, + "args": { + "External id": 1409127,"Record function id": 0, "Ev Idx": 1638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.24", "pid": 2338710, "tid": 2379450, + "ts": 6410531420334.922, "dur": 1133.212, + "args": { + "External id": 1409128,"Record function id": 0, "Ev Idx": 1639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410531420355.392, "dur": 1093.888, + "args": { + "External id": 1409129,"Record function id": 0, "Ev Idx": 1640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531420479.084, "dur": 8.086, + "args": { + "External id": 1409130,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531420506.900, "dur": 48.117, + "args": { + "External id": 1409131,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420517.450, "dur": 1.641, + "args": { + "External id": 1409132,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420523.443, "dur": 0.635, + "args": { + "External id": 1409133,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420524.887, "dur": 0.725, + "args": { + "External id": 1409134,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420529.726, "dur": 2.581, + "args": { + "External id": 1409135,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420533.283, "dur": 2.971, + "args": { + "External id": 1409136,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420539.367, "dur": 0.453, + "args": { + "External id": 1409137,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420542.100, "dur": 0.313, + "args": { + "External id": 1409138,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420543.748, "dur": 0.423, + "args": { + "External id": 1409139,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420547.526, "dur": 0.308, + "args": { + "External id": 1409140,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531420569.849, "dur": 53.517, + "args": { + "External id": 1409141,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410531420675.906, "dur": 151.567, + "args": { + "External id": 1409142,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 1653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531420690.186, "dur": 5.420, + "args": { + "External id": 1409143,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410531420702.507, "dur": 14.200, + "args": { + "External id": 1409144,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531420706.656, "dur": 9.576, + "args": { + "External id": 1409145,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 1656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420712.000, "dur": 2.807, + "args": { + "External id": 1409146,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531420724.661, "dur": 35.593, + "args": { + "External id": 1409147,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420726.300, "dur": 0.480, + "args": { + "External id": 1409148,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420729.907, "dur": 3.233, + "args": { + "External id": 1409149,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420733.967, "dur": 0.586, + "args": { + "External id": 1409150,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420740.268, "dur": 0.516, + "args": { + "External id": 1409151,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420741.558, "dur": 0.420, + "args": { + "External id": 1409152,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420742.985, "dur": 2.260, + "args": { + "External id": 1409153,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420748.044, "dur": 0.650, + "args": { + "External id": 1409154,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420749.562, "dur": 0.535, + "args": { + "External id": 1409155,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531420753.146, "dur": 0.358, + "args": { + "External id": 1409156,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531420776.555, "dur": 38.942, + "args": { + "External id": 1409157,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531420899.706, "dur": 400.719, + "args": { + "External id": 1409158,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 1669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531420939.342, "dur": 354.003, + "args": { + "External id": 1409159,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1670, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531420951.058, "dur": 334.503, + "args": { + "External id": 1409160,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531421329.995, "dur": 3.176, + "args": { + "External id": 1409161,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1672, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531421489.538, "dur": 2072.481, + "args": { + "External id": 1409162,"Sequence number": 15108894, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1673 + } + }, + { + "ph": "f", "id": 172, "pid": 2338710, "tid": 2379450, "ts": 6410531421489.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531421637.975, "dur": 126.831, + "args": { + "External id": 1409163,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 1674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531421815.165, "dur": 47.316, + "args": { + "External id": 1409164,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531421886.540, "dur": 55.725, + "args": { + "External id": 1409165,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 1676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531421954.306, "dur": 35.501, + "args": { + "External id": 1409166,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531421997.184, "dur": 36.452, + "args": { + "External id": 1409167,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531422041.211, "dur": 78.295, + "args": { + "External id": 1409168,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531422137.199, "dur": 40.940, + "args": { + "External id": 1409169,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531422215.286, "dur": 29.720, + "args": { + "External id": 1409170,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 1681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531422269.403, "dur": 32.915, + "args": { + "External id": 1409171,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531422329.445, "dur": 21.162, + "args": { + "External id": 1409172,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531422370.986, "dur": 16.578, + "args": { + "External id": 1409173,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 1684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531422399.263, "dur": 61.740, + "args": { + "External id": 1409174,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 1685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531422467.774, "dur": 39.432, + "args": { + "External id": 1409175,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 1686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531422543.429, "dur": 287.563, + "args": { + "External id": 1409176,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531422642.202, "dur": 8.314, + "args": { + "External id": 1409177,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531422652.661, "dur": 2.287, + "args": { + "External id": 1409178,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531422656.436, "dur": 1.858, + "args": { + "External id": 1409179,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531422659.405, "dur": 3.528, + "args": { + "External id": 1409180,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531422708.259, "dur": 10.199, + "args": { + "External id": 1409181,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531422712.472, "dur": 5.735, + "args": { + "External id": 1409182,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531422721.041, "dur": 33.478, + "args": { + "External id": 1409183,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531422726.805, "dur": 1.995, + "args": { + "External id": 1409184,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531422756.022, "dur": 4.929, + "args": { + "External id": 1409185,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531422760.218, "dur": 0.614, + "args": { + "External id": 1409186,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531422761.831, "dur": 16.582, + "args": { + "External id": 1409187,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531422764.842, "dur": 0.739, + "args": { + "External id": 1409188,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531422876.194, "dur": 33.785, + "args": { + "External id": 1409189,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531422929.507, "dur": 16.473, + "args": { + "External id": 1409190,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531422953.989, "dur": 44.796, + "args": { + "External id": 1409191,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 1702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531423006.592, "dur": 41.006, + "args": { + "External id": 1409192,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531423104.115, "dur": 32.469, + "args": { + "External id": 1409193,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 1704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531423145.298, "dur": 36.889, + "args": { + "External id": 1409194,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 1705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531423191.130, "dur": 31.300, + "args": { + "External id": 1409195,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 1706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531423230.002, "dur": 34.050, + "args": { + "External id": 1409196,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 1707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410531423292.918, "dur": 30.074, + "args": { + "External id": 1409197,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 1708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531423346.741, "dur": 32.033, + "args": { + "External id": 1409198,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531423401.101, "dur": 36.751, + "args": { + "External id": 1409199,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 1710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531423468.864, "dur": 19.251, + "args": { + "External id": 1409200,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 1711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410531423506.939, "dur": 18.875, + "args": { + "External id": 1409201,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 1712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423614.897, "dur": 19.462, + "args": { + "External id": 1409202,"Record function id": 0, "Ev Idx": 1713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423618.599, "dur": 14.607, + "args": { + "External id": 1409203,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423623.639, "dur": 8.334, + "args": { + "External id": 1409204,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423625.404, "dur": 6.433, + "args": { + "External id": 1409205,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423638.986, "dur": 5.760, + "args": { + "External id": 1409206,"Record function id": 0, "Ev Idx": 1717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423640.473, "dur": 3.646, + "args": { + "External id": 1409207,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423641.833, "dur": 1.742, + "args": { + "External id": 1409208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423642.488, "dur": 0.945, + "args": { + "External id": 1409209,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423648.650, "dur": 7.717, + "args": { + "External id": 1409210,"Record function id": 0, "Ev Idx": 1721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423649.944, "dur": 5.916, + "args": { + "External id": 1409211,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423650.953, "dur": 4.381, + "args": { + "External id": 1409212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423651.653, "dur": 3.579, + "args": { + "External id": 1409213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423660.199, "dur": 4.641, + "args": { + "External id": 1409214,"Record function id": 0, "Ev Idx": 1725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423661.366, "dur": 2.997, + "args": { + "External id": 1409215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423662.485, "dur": 1.311, + "args": { + "External id": 1409216,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423662.910, "dur": 0.767, + "args": { + "External id": 1409217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423668.792, "dur": 13.609, + "args": { + "External id": 1409218,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423670.308, "dur": 11.564, + "args": { + "External id": 1409219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423680.118, "dur": 1.168, + "args": { + "External id": 1409220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423680.495, "dur": 0.704, + "args": { + "External id": 1409221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423686.138, "dur": 8.590, + "args": { + "External id": 1409222,"Record function id": 0, "Ev Idx": 1733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423689.146, "dur": 5.090, + "args": { + "External id": 1409223,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423689.953, "dur": 3.713, + "args": { + "External id": 1409224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423692.755, "dur": 0.785, + "args": { + "External id": 1409225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423701.073, "dur": 4.367, + "args": { + "External id": 1409226,"Record function id": 0, "Ev Idx": 1737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423702.282, "dur": 2.679, + "args": { + "External id": 1409227,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423703.286, "dur": 1.157, + "args": { + "External id": 1409228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423703.631, "dur": 0.709, + "args": { + "External id": 1409229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423709.413, "dur": 4.861, + "args": { + "External id": 1409230,"Record function id": 0, "Ev Idx": 1741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423710.576, "dur": 3.200, + "args": { + "External id": 1409231,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423711.627, "dur": 1.444, + "args": { + "External id": 1409232,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423712.153, "dur": 0.836, + "args": { + "External id": 1409233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423718.066, "dur": 3.935, + "args": { + "External id": 1409234,"Record function id": 0, "Ev Idx": 1745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531423719.142, "dur": 2.378, + "args": { + "External id": 1409235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423719.725, "dur": 1.267, + "args": { + "External id": 1409236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531423720.153, "dur": 0.716, + "args": { + "External id": 1409237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531423727.302, "dur": 277921.780, + "args": { + "External id": 1409238,"Record function id": 0, "Sequence number": 15108893, "Fwd thread id": 1, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531423728.988, "dur": 277909.451, + "args": { + "External id": 1409239,"Sequence number": 15108893, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1750 + } + }, + { + "ph": "f", "id": 173, "pid": 2338710, "tid": 2379450, "ts": 6410531423728.988, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 2338710, "tid": 2379450, + "ts": 6410531423767.686, "dur": 49.931, + "args": { + "External id": 1409240,"Record function id": 0, "Ev Idx": 1751 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 2338710, "tid": 2379450, + "ts": 6410531423830.411, "dur": 96.406, + "args": { + "External id": 1409241,"Record function id": 0, "Ev Idx": 1752 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 2338710, "tid": 2379450, + "ts": 6410531423933.524, "dur": 277694.492, + "args": { + "External id": 1409242,"Record function id": 0, "Ev Idx": 1753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531423997.752, "dur": 8.740, + "args": { + "External id": 1409243,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531424016.708, "dur": 7.444, + "args": { + "External id": 1409244,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 1755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531424042.632, "dur": 276576.980, + "args": { + "External id": 1409245,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 1756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531424100.767, "dur": 276502.686, + "args": { + "External id": 1409246,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 1757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531424231.482, "dur": 6.667, + "args": { + "External id": 1409247,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531424263.254, "dur": 276278.571, + "args": { + "External id": 1409248,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 1759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531424266.441, "dur": 276273.808, + "args": { + "External id": 1409249,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 1760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531424270.931, "dur": 17.560, + "args": { + "External id": 1409250,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531424291.169, "dur": 276241.607, + "args": { + "External id": 1409251,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 1762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531700758.740, "dur": 24.138, + "args": { + "External id": 1409252,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 1763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531700769.727, "dur": 12.663, + "args": { + "External id": 1409253,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531700826.329, "dur": 396.337, + "args": { + "External id": 1409254,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 1765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531700866.589, "dur": 349.865, + "args": { + "External id": 1409255,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1766, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531700879.942, "dur": 329.450, + "args": { + "External id": 1409256,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 1767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531701250.406, "dur": 2.726, + "args": { + "External id": 1409257,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1768, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701326.089, "dur": 8.054, + "args": { + "External id": 1409258,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701400.830, "dur": 1.619, + "args": { + "External id": 1409259,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701441.935, "dur": 4.903, + "args": { + "External id": 1409260,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701467.215, "dur": 1.127, + "args": { + "External id": 1409261,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701483.437, "dur": 1.047, + "args": { + "External id": 1409262,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701497.947, "dur": 1.263, + "args": { + "External id": 1409263,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701513.916, "dur": 3.835, + "args": { + "External id": 1409264,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701532.074, "dur": 3.444, + "args": { + "External id": 1409265,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701549.438, "dur": 1.263, + "args": { + "External id": 1409266,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531701667.400, "dur": 3554.599, + "args": { + "External id": 1409267,"Record function id": 0, "Ev Idx": 1778 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410531701693.497, "dur": 1339.559, + "args": { + "External id": 1409268,"Record function id": 0, "Ev Idx": 1779 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410531701711.485, "dur": 458.798, + "args": { + "External id": 1409269,"Record function id": 0, "Ev Idx": 1780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701825.383, "dur": 5.050, + "args": { + "External id": 1409270,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 1781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701834.318, "dur": 1.153, + "args": { + "External id": 1409271,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 1782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701837.483, "dur": 3.459, + "args": { + "External id": 1409272,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 1783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701842.831, "dur": 0.981, + "args": { + "External id": 1409273,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701847.872, "dur": 1.085, + "args": { + "External id": 1409274,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701850.603, "dur": 0.976, + "args": { + "External id": 1409275,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 1786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701854.994, "dur": 3.396, + "args": { + "External id": 1409276,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 1787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701859.872, "dur": 1.089, + "args": { + "External id": 1409277,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701864.154, "dur": 1.095, + "args": { + "External id": 1409278,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531701867.010, "dur": 1.019, + "args": { + "External id": 1409279,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531701890.627, "dur": 237.885, + "args": { + "External id": 1409280,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 1791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531701911.663, "dur": 209.554, + "args": { + "External id": 1409281,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 1792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531701931.218, "dur": 18.419, + "args": { + "External id": 1409282,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531701956.045, "dur": 85.757, + "args": { + "External id": 1409283,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 1794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531701958.892, "dur": 82.417, + "args": { + "External id": 1409284,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 1795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531701965.470, "dur": 7.720, + "args": { + "External id": 1409285,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531701978.392, "dur": 62.145, + "args": { + "External id": 1409286,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 1797 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.23", "pid": 2338710, "tid": 2379450, + "ts": 6410531702281.791, "dur": 741.491, + "args": { + "External id": 1409287,"Record function id": 0, "Ev Idx": 1798 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410531702303.107, "dur": 705.104, + "args": { + "External id": 1409288,"Record function id": 0, "Ev Idx": 1799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531702379.554, "dur": 6.430, + "args": { + "External id": 1409289,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531702404.015, "dur": 61.759, + "args": { + "External id": 1409290,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702411.258, "dur": 1.920, + "args": { + "External id": 1409291,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702429.612, "dur": 2.778, + "args": { + "External id": 1409292,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702434.569, "dur": 0.614, + "args": { + "External id": 1409293,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702438.093, "dur": 0.834, + "args": { + "External id": 1409294,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702442.432, "dur": 0.638, + "args": { + "External id": 1409295,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702445.759, "dur": 3.139, + "args": { + "External id": 1409296,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702450.243, "dur": 0.371, + "args": { + "External id": 1409297,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702454.118, "dur": 0.286, + "args": { + "External id": 1409298,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702456.898, "dur": 0.274, + "args": { + "External id": 1409299,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531702479.088, "dur": 54.323, + "args": { + "External id": 1409300,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410531702574.113, "dur": 150.439, + "args": { + "External id": 1409301,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531702586.464, "dur": 5.468, + "args": { + "External id": 1409302,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410531702598.685, "dur": 20.453, + "args": { + "External id": 1409303,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531702610.722, "dur": 7.939, + "args": { + "External id": 1409304,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 1815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702616.223, "dur": 0.725, + "args": { + "External id": 1409305,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531702627.293, "dur": 34.563, + "args": { + "External id": 1409306,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702629.127, "dur": 0.593, + "args": { + "External id": 1409307,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702634.962, "dur": 0.582, + "args": { + "External id": 1409308,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702636.858, "dur": 2.807, + "args": { + "External id": 1409309,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702642.592, "dur": 2.424, + "args": { + "External id": 1409310,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702645.608, "dur": 0.698, + "args": { + "External id": 1409311,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702646.906, "dur": 0.530, + "args": { + "External id": 1409312,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702650.992, "dur": 0.380, + "args": { + "External id": 1409313,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702652.113, "dur": 0.679, + "args": { + "External id": 1409314,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531702653.981, "dur": 0.529, + "args": { + "External id": 1409315,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531702678.640, "dur": 36.458, + "args": { + "External id": 1409316,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531702780.138, "dur": 145.317, + "args": { + "External id": 1409317,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531702816.860, "dur": 104.312, + "args": { + "External id": 1409318,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1829, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531702827.894, "dur": 88.404, + "args": { + "External id": 1409319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 1830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531702947.083, "dur": 1.938, + "args": { + "External id": 1409320,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1831, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531703040.860, "dur": 2152.575, + "args": { + "External id": 1409321,"Sequence number": 15108892, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1832 + } + }, + { + "ph": "f", "id": 174, "pid": 2338710, "tid": 2379450, "ts": 6410531703040.860, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531703218.126, "dur": 127.260, + "args": { + "External id": 1409322,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 1833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531703395.533, "dur": 71.514, + "args": { + "External id": 1409323,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 1834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531703491.655, "dur": 64.282, + "args": { + "External id": 1409324,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 1835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531703572.051, "dur": 38.245, + "args": { + "External id": 1409325,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531703620.799, "dur": 38.252, + "args": { + "External id": 1409326,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531703666.463, "dur": 32.162, + "args": { + "External id": 1409327,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531703708.008, "dur": 32.235, + "args": { + "External id": 1409328,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531703773.824, "dur": 32.894, + "args": { + "External id": 1409329,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531703831.493, "dur": 33.679, + "args": { + "External id": 1409330,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531703894.077, "dur": 23.733, + "args": { + "External id": 1409331,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 1842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531703937.127, "dur": 20.587, + "args": { + "External id": 1409332,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 1843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531703966.159, "dur": 43.568, + "args": { + "External id": 1409333,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531704013.650, "dur": 36.632, + "args": { + "External id": 1409334,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 1845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531704133.938, "dur": 342.604, + "args": { + "External id": 1409335,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531704249.602, "dur": 8.787, + "args": { + "External id": 1409336,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531704261.118, "dur": 2.821, + "args": { + "External id": 1409337,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531704265.461, "dur": 2.514, + "args": { + "External id": 1409338,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531704269.087, "dur": 3.273, + "args": { + "External id": 1409339,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531704330.248, "dur": 5.875, + "args": { + "External id": 1409340,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531704332.590, "dur": 3.358, + "args": { + "External id": 1409341,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531704338.643, "dur": 44.918, + "args": { + "External id": 1409342,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531704345.078, "dur": 6.136, + "args": { + "External id": 1409343,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531704385.815, "dur": 1.858, + "args": { + "External id": 1409344,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531704386.978, "dur": 0.580, + "args": { + "External id": 1409345,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531704389.122, "dur": 19.712, + "args": { + "External id": 1409346,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531704394.000, "dur": 0.453, + "args": { + "External id": 1409347,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531704527.983, "dur": 38.568, + "args": { + "External id": 1409348,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531704587.708, "dur": 19.399, + "args": { + "External id": 1409349,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531704616.242, "dur": 59.695, + "args": { + "External id": 1409350,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 1861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531704683.645, "dur": 46.034, + "args": { + "External id": 1409351,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 1862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531704741.902, "dur": 25.631, + "args": { + "External id": 1409352,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 1863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531704773.648, "dur": 35.168, + "args": { + "External id": 1409353,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 1864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531704816.553, "dur": 31.502, + "args": { + "External id": 1409354,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 1865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531704855.811, "dur": 33.358, + "args": { + "External id": 1409355,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 1866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410531704913.992, "dur": 31.817, + "args": { + "External id": 1409356,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 1867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531704964.559, "dur": 30.491, + "args": { + "External id": 1409357,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531705013.190, "dur": 23.260, + "args": { + "External id": 1409358,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 1869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531705094.448, "dur": 23.315, + "args": { + "External id": 1409359,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 1870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410531705139.438, "dur": 18.855, + "args": { + "External id": 1409360,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 1871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705248.001, "dur": 16.563, + "args": { + "External id": 1409361,"Record function id": 0, "Ev Idx": 1872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705251.448, "dur": 12.052, + "args": { + "External id": 1409362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705256.598, "dur": 5.765, + "args": { + "External id": 1409363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705257.990, "dur": 4.262, + "args": { + "External id": 1409364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705269.214, "dur": 6.092, + "args": { + "External id": 1409365,"Record function id": 0, "Ev Idx": 1876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705270.867, "dur": 3.792, + "args": { + "External id": 1409366,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705272.152, "dur": 1.955, + "args": { + "External id": 1409367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705272.814, "dur": 1.184, + "args": { + "External id": 1409368,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705279.290, "dur": 7.949, + "args": { + "External id": 1409369,"Record function id": 0, "Ev Idx": 1880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705280.684, "dur": 5.991, + "args": { + "External id": 1409370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705281.954, "dur": 4.112, + "args": { + "External id": 1409371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705282.638, "dur": 3.297, + "args": { + "External id": 1409372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705291.187, "dur": 5.643, + "args": { + "External id": 1409373,"Record function id": 0, "Ev Idx": 1884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705292.713, "dur": 3.579, + "args": { + "External id": 1409374,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705293.818, "dur": 1.991, + "args": { + "External id": 1409375,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705294.524, "dur": 1.199, + "args": { + "External id": 1409376,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705300.505, "dur": 4.505, + "args": { + "External id": 1409377,"Record function id": 0, "Ev Idx": 1888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705302.113, "dur": 2.430, + "args": { + "External id": 1409378,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705302.845, "dur": 1.185, + "args": { + "External id": 1409379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705303.236, "dur": 0.707, + "args": { + "External id": 1409380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705308.624, "dur": 4.505, + "args": { + "External id": 1409381,"Record function id": 0, "Ev Idx": 1892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705310.299, "dur": 2.331, + "args": { + "External id": 1409382,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705310.985, "dur": 1.159, + "args": { + "External id": 1409383,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705311.416, "dur": 0.639, + "args": { + "External id": 1409384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705316.910, "dur": 13.237, + "args": { + "External id": 1409385,"Record function id": 0, "Ev Idx": 1896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705318.223, "dur": 11.420, + "args": { + "External id": 1409386,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705319.071, "dur": 9.960, + "args": { + "External id": 1409387,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705327.990, "dur": 0.886, + "args": { + "External id": 1409388,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705333.833, "dur": 5.243, + "args": { + "External id": 1409389,"Record function id": 0, "Ev Idx": 1900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705335.226, "dur": 3.209, + "args": { + "External id": 1409390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705336.023, "dur": 1.794, + "args": { + "External id": 1409391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705336.632, "dur": 1.082, + "args": { + "External id": 1409392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705342.651, "dur": 4.242, + "args": { + "External id": 1409393,"Record function id": 0, "Ev Idx": 1904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531705343.842, "dur": 2.528, + "args": { + "External id": 1409394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705344.570, "dur": 1.183, + "args": { + "External id": 1409395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531705344.969, "dur": 0.694, + "args": { + "External id": 1409396,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531705351.739, "dur": 75755.358, + "args": { + "External id": 1409397,"Record function id": 0, "Sequence number": 15108891, "Fwd thread id": 1, "Ev Idx": 1908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531705353.399, "dur": 75741.401, + "args": { + "External id": 1409398,"Sequence number": 15108891, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1909 + } + }, + { + "ph": "f", "id": 175, "pid": 2338710, "tid": 2379450, "ts": 6410531705353.399, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410531705392.397, "dur": 62.919, + "args": { + "External id": 1409399,"Record function id": 0, "Ev Idx": 1910 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410531705466.935, "dur": 78.232, + "args": { + "External id": 1409400,"Record function id": 0, "Ev Idx": 1911 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410531705552.881, "dur": 75492.250, + "args": { + "External id": 1409401,"Record function id": 0, "Ev Idx": 1912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531705659.511, "dur": 9.437, + "args": { + "External id": 1409402,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531705681.948, "dur": 7.563, + "args": { + "External id": 1409403,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 1914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531705707.808, "dur": 74476.502, + "args": { + "External id": 1409404,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 1915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531705725.509, "dur": 74442.498, + "args": { + "External id": 1409405,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 1916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531705859.879, "dur": 23.085, + "args": { + "External id": 1409406,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531705910.612, "dur": 74199.826, + "args": { + "External id": 1409407,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 1918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531705913.855, "dur": 74195.014, + "args": { + "External id": 1409408,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 1919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531705919.081, "dur": 14.476, + "args": { + "External id": 1409409,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531705935.823, "dur": 74166.104, + "args": { + "External id": 1409410,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 1921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531780315.986, "dur": 16.092, + "args": { + "External id": 1409411,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 1922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531780320.612, "dur": 10.950, + "args": { + "External id": 1409412,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531780369.365, "dur": 317.266, + "args": { + "External id": 1409413,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 1924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531780406.436, "dur": 273.956, + "args": { + "External id": 1409414,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1925, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531780437.108, "dur": 237.819, + "args": { + "External id": 1409415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 1926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531780715.271, "dur": 2.398, + "args": { + "External id": 1409416,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1927, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780782.856, "dur": 7.647, + "args": { + "External id": 1409417,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780845.772, "dur": 1.640, + "args": { + "External id": 1409418,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780866.598, "dur": 4.151, + "args": { + "External id": 1409419,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780886.532, "dur": 1.535, + "args": { + "External id": 1409420,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780905.002, "dur": 1.030, + "args": { + "External id": 1409421,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780919.359, "dur": 1.013, + "args": { + "External id": 1409422,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780933.031, "dur": 3.829, + "args": { + "External id": 1409423,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780951.145, "dur": 3.703, + "args": { + "External id": 1409424,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531780968.727, "dur": 0.886, + "args": { + "External id": 1409425,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531781126.005, "dur": 3589.604, + "args": { + "External id": 1409426,"Record function id": 0, "Ev Idx": 1937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410531781153.316, "dur": 1338.878, + "args": { + "External id": 1409427,"Record function id": 0, "Ev Idx": 1938 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410531781172.431, "dur": 434.888, + "args": { + "External id": 1409428,"Record function id": 0, "Ev Idx": 1939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781282.565, "dur": 5.829, + "args": { + "External id": 1409429,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 1940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781292.372, "dur": 1.220, + "args": { + "External id": 1409430,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 1941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781295.641, "dur": 3.840, + "args": { + "External id": 1409431,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 1942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781301.782, "dur": 1.792, + "args": { + "External id": 1409432,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781305.152, "dur": 0.876, + "args": { + "External id": 1409433,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781307.766, "dur": 1.186, + "args": { + "External id": 1409434,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 1945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781310.810, "dur": 3.598, + "args": { + "External id": 1409435,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 1946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781318.698, "dur": 1.400, + "args": { + "External id": 1409436,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781321.932, "dur": 1.166, + "args": { + "External id": 1409437,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531781324.983, "dur": 1.131, + "args": { + "External id": 1409438,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531781360.683, "dur": 204.521, + "args": { + "External id": 1409439,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 1950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531781381.388, "dur": 177.446, + "args": { + "External id": 1409440,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 1951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531781401.210, "dur": 33.122, + "args": { + "External id": 1409441,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531781442.543, "dur": 82.382, + "args": { + "External id": 1409442,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 1953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531781445.713, "dur": 78.760, + "args": { + "External id": 1409443,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 1954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781450.502, "dur": 8.713, + "args": { + "External id": 1409444,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531781461.552, "dur": 62.139, + "args": { + "External id": 1409445,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 1956 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.22", "pid": 2338710, "tid": 2379450, + "ts": 6410531781713.778, "dur": 769.571, + "args": { + "External id": 1409446,"Record function id": 0, "Ev Idx": 1957 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410531781733.933, "dur": 733.480, + "args": { + "External id": 1409447,"Record function id": 0, "Ev Idx": 1958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531781809.156, "dur": 6.758, + "args": { + "External id": 1409448,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531781834.047, "dur": 44.417, + "args": { + "External id": 1409449,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781839.698, "dur": 2.099, + "args": { + "External id": 1409450,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781844.702, "dur": 2.295, + "args": { + "External id": 1409451,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781848.477, "dur": 0.371, + "args": { + "External id": 1409452,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781850.428, "dur": 0.427, + "args": { + "External id": 1409453,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781858.171, "dur": 0.622, + "args": { + "External id": 1409454,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781860.512, "dur": 2.550, + "args": { + "External id": 1409455,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781864.618, "dur": 0.436, + "args": { + "External id": 1409456,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781868.199, "dur": 0.300, + "args": { + "External id": 1409457,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531781869.803, "dur": 0.333, + "args": { + "External id": 1409458,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531781890.454, "dur": 54.345, + "args": { + "External id": 1409459,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410531781982.371, "dur": 177.263, + "args": { + "External id": 1409460,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 1971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531781994.440, "dur": 3.802, + "args": { + "External id": 1409461,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410531782004.093, "dur": 12.185, + "args": { + "External id": 1409462,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531782008.960, "dur": 6.826, + "args": { + "External id": 1409463,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 1974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782013.359, "dur": 0.717, + "args": { + "External id": 1409464,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531782024.381, "dur": 71.573, + "args": { + "External id": 1409465,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782026.667, "dur": 0.652, + "args": { + "External id": 1409466,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782031.292, "dur": 0.495, + "args": { + "External id": 1409467,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782033.473, "dur": 2.653, + "args": { + "External id": 1409468,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782037.835, "dur": 1.912, + "args": { + "External id": 1409469,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782041.032, "dur": 0.528, + "args": { + "External id": 1409470,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782043.089, "dur": 0.324, + "args": { + "External id": 1409471,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782046.780, "dur": 0.452, + "args": { + "External id": 1409472,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782048.754, "dur": 0.333, + "args": { + "External id": 1409473,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531782050.493, "dur": 0.250, + "args": { + "External id": 1409474,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531782112.273, "dur": 37.116, + "args": { + "External id": 1409475,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531782216.409, "dur": 147.348, + "args": { + "External id": 1409476,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 1987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531782253.215, "dur": 106.636, + "args": { + "External id": 1409477,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1988, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531782264.034, "dur": 91.205, + "args": { + "External id": 1409478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531782384.224, "dur": 2.383, + "args": { + "External id": 1409479,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1990, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531782501.561, "dur": 2184.426, + "args": { + "External id": 1409480,"Sequence number": 15108890, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1991 + } + }, + { + "ph": "f", "id": 176, "pid": 2338710, "tid": 2379450, "ts": 6410531782501.561, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531782632.640, "dur": 124.727, + "args": { + "External id": 1409481,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 1992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531782805.396, "dur": 47.527, + "args": { + "External id": 1409482,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531782872.530, "dur": 59.006, + "args": { + "External id": 1409483,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 1994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531782945.854, "dur": 38.061, + "args": { + "External id": 1409484,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531782991.615, "dur": 37.240, + "args": { + "External id": 1409485,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531783038.330, "dur": 76.819, + "args": { + "External id": 1409486,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531783130.205, "dur": 38.634, + "args": { + "External id": 1409487,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531783203.369, "dur": 30.767, + "args": { + "External id": 1409488,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 1999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531783256.242, "dur": 33.380, + "args": { + "External id": 1409489,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531783317.002, "dur": 22.831, + "args": { + "External id": 1409490,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531783355.709, "dur": 20.850, + "args": { + "External id": 1409491,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531783385.519, "dur": 61.730, + "args": { + "External id": 1409492,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531783453.799, "dur": 41.444, + "args": { + "External id": 1409493,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531783533.546, "dur": 329.667, + "args": { + "External id": 1409494,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531783628.775, "dur": 7.998, + "args": { + "External id": 1409495,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531783639.151, "dur": 2.698, + "args": { + "External id": 1409496,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531783643.276, "dur": 1.860, + "args": { + "External id": 1409497,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531783646.386, "dur": 1.791, + "args": { + "External id": 1409498,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531783702.277, "dur": 5.616, + "args": { + "External id": 1409499,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531783704.705, "dur": 2.976, + "args": { + "External id": 1409500,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531783709.909, "dur": 55.808, + "args": { + "External id": 1409501,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531783716.157, "dur": 6.019, + "args": { + "External id": 1409502,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531783771.854, "dur": 2.731, + "args": { + "External id": 1409503,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531783773.384, "dur": 1.128, + "args": { + "External id": 1409504,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531783776.368, "dur": 22.545, + "args": { + "External id": 1409505,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531783779.817, "dur": 0.753, + "args": { + "External id": 1409506,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531783911.199, "dur": 38.929, + "args": { + "External id": 1409507,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531783972.365, "dur": 18.388, + "args": { + "External id": 1409508,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531783999.628, "dur": 49.679, + "args": { + "External id": 1409509,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531784095.941, "dur": 70.448, + "args": { + "External id": 1409510,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531784188.757, "dur": 40.054, + "args": { + "External id": 1409511,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531784240.077, "dur": 51.594, + "args": { + "External id": 1409512,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531784304.358, "dur": 35.052, + "args": { + "External id": 1409513,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531784347.661, "dur": 35.214, + "args": { + "External id": 1409514,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410531784430.631, "dur": 40.007, + "args": { + "External id": 1409515,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531784495.353, "dur": 31.942, + "args": { + "External id": 1409516,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531784548.403, "dur": 22.849, + "args": { + "External id": 1409517,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531784593.871, "dur": 19.018, + "args": { + "External id": 1409518,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410531784631.769, "dur": 17.993, + "args": { + "External id": 1409519,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784741.876, "dur": 18.488, + "args": { + "External id": 1409520,"Record function id": 0, "Ev Idx": 2031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784746.065, "dur": 13.111, + "args": { + "External id": 1409521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784751.229, "dur": 6.650, + "args": { + "External id": 1409522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784752.982, "dur": 4.783, + "args": { + "External id": 1409523,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784765.026, "dur": 5.950, + "args": { + "External id": 1409524,"Record function id": 0, "Ev Idx": 2035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784766.718, "dur": 3.718, + "args": { + "External id": 1409525,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784768.072, "dur": 1.765, + "args": { + "External id": 1409526,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784768.907, "dur": 0.837, + "args": { + "External id": 1409527,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784775.147, "dur": 7.249, + "args": { + "External id": 1409528,"Record function id": 0, "Ev Idx": 2039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784776.792, "dur": 5.105, + "args": { + "External id": 1409529,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784777.509, "dur": 3.909, + "args": { + "External id": 1409530,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784778.139, "dur": 3.152, + "args": { + "External id": 1409531,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784786.199, "dur": 4.756, + "args": { + "External id": 1409532,"Record function id": 0, "Ev Idx": 2043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784787.552, "dur": 2.907, + "args": { + "External id": 1409533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784788.306, "dur": 1.680, + "args": { + "External id": 1409534,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784789.066, "dur": 0.819, + "args": { + "External id": 1409535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784794.639, "dur": 42.706, + "args": { + "External id": 1409536,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784834.152, "dur": 2.676, + "args": { + "External id": 1409537,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784834.886, "dur": 1.276, + "args": { + "External id": 1409538,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784835.285, "dur": 0.780, + "args": { + "External id": 1409539,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784841.437, "dur": 8.810, + "args": { + "External id": 1409540,"Record function id": 0, "Ev Idx": 2051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784844.510, "dur": 5.215, + "args": { + "External id": 1409541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784845.550, "dur": 3.695, + "args": { + "External id": 1409542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784848.301, "dur": 0.835, + "args": { + "External id": 1409543,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784855.306, "dur": 4.427, + "args": { + "External id": 1409544,"Record function id": 0, "Ev Idx": 2055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784856.818, "dur": 2.409, + "args": { + "External id": 1409545,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784857.485, "dur": 1.145, + "args": { + "External id": 1409546,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784857.797, "dur": 0.744, + "args": { + "External id": 1409547,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784863.443, "dur": 4.795, + "args": { + "External id": 1409548,"Record function id": 0, "Ev Idx": 2059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784864.859, "dur": 2.899, + "args": { + "External id": 1409549,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784865.759, "dur": 1.534, + "args": { + "External id": 1409550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784866.323, "dur": 0.844, + "args": { + "External id": 1409551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784871.876, "dur": 4.273, + "args": { + "External id": 1409552,"Record function id": 0, "Ev Idx": 2063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531784873.019, "dur": 2.632, + "args": { + "External id": 1409553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784873.592, "dur": 1.602, + "args": { + "External id": 1409554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531784874.320, "dur": 0.760, + "args": { + "External id": 1409555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531784880.966, "dur": 72664.588, + "args": { + "External id": 1409556,"Record function id": 0, "Sequence number": 15108889, "Fwd thread id": 1, "Ev Idx": 2067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531784885.006, "dur": 72648.852, + "args": { + "External id": 1409557,"Sequence number": 15108889, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2068 + } + }, + { + "ph": "f", "id": 177, "pid": 2338710, "tid": 2379450, "ts": 6410531784885.006, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410531784923.675, "dur": 49.098, + "args": { + "External id": 1409558,"Record function id": 0, "Ev Idx": 2069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410531784982.562, "dur": 121.426, + "args": { + "External id": 1409559,"Record function id": 0, "Ev Idx": 2070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410531785113.784, "dur": 72410.787, + "args": { + "External id": 1409560,"Record function id": 0, "Ev Idx": 2071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531785226.905, "dur": 8.867, + "args": { + "External id": 1409561,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531785248.453, "dur": 8.186, + "args": { + "External id": 1409562,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531785276.824, "dur": 71156.181, + "args": { + "External id": 1409563,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531785292.676, "dur": 71112.290, + "args": { + "External id": 1409564,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531785404.351, "dur": 54.036, + "args": { + "External id": 1409565,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531785494.872, "dur": 70850.268, + "args": { + "External id": 1409566,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531785498.384, "dur": 70845.443, + "args": { + "External id": 1409567,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531785505.619, "dur": 17.160, + "args": { + "External id": 1409568,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531785525.392, "dur": 70812.154, + "args": { + "External id": 1409569,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531856563.093, "dur": 16.593, + "args": { + "External id": 1409570,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531856567.886, "dur": 11.339, + "args": { + "External id": 1409571,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531856617.279, "dur": 515.613, + "args": { + "External id": 1409572,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531856654.683, "dur": 470.864, + "args": { + "External id": 1409573,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2084, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531856671.482, "dur": 446.330, + "args": { + "External id": 1409574,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531857162.812, "dur": 3.112, + "args": { + "External id": 1409575,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2086, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857244.677, "dur": 8.324, + "args": { + "External id": 1409576,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857308.967, "dur": 1.757, + "args": { + "External id": 1409577,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857329.584, "dur": 3.821, + "args": { + "External id": 1409578,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857347.262, "dur": 1.499, + "args": { + "External id": 1409579,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857363.469, "dur": 1.083, + "args": { + "External id": 1409580,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857377.712, "dur": 1.333, + "args": { + "External id": 1409581,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857392.806, "dur": 3.593, + "args": { + "External id": 1409582,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857408.860, "dur": 3.536, + "args": { + "External id": 1409583,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857447.340, "dur": 1.743, + "args": { + "External id": 1409584,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531857563.972, "dur": 3461.996, + "args": { + "External id": 1409585,"Record function id": 0, "Ev Idx": 2096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410531857588.641, "dur": 1303.711, + "args": { + "External id": 1409586,"Record function id": 0, "Ev Idx": 2097 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410531857605.953, "dur": 396.515, + "args": { + "External id": 1409587,"Record function id": 0, "Ev Idx": 2098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857716.121, "dur": 5.012, + "args": { + "External id": 1409588,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857725.114, "dur": 1.268, + "args": { + "External id": 1409589,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857728.428, "dur": 3.233, + "args": { + "External id": 1409590,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857734.145, "dur": 1.148, + "args": { + "External id": 1409591,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857737.048, "dur": 0.972, + "args": { + "External id": 1409592,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857740.005, "dur": 0.983, + "args": { + "External id": 1409593,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857743.002, "dur": 3.013, + "args": { + "External id": 1409594,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857749.874, "dur": 1.262, + "args": { + "External id": 1409595,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857752.849, "dur": 1.724, + "args": { + "External id": 1409596,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531857756.210, "dur": 0.962, + "args": { + "External id": 1409597,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531857778.292, "dur": 185.151, + "args": { + "External id": 1409598,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531857797.569, "dur": 160.140, + "args": { + "External id": 1409599,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531857823.990, "dur": 18.943, + "args": { + "External id": 1409600,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531857847.308, "dur": 78.702, + "args": { + "External id": 1409601,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531857851.885, "dur": 73.716, + "args": { + "External id": 1409602,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531857856.476, "dur": 7.121, + "args": { + "External id": 1409603,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531857865.468, "dur": 59.067, + "args": { + "External id": 1409604,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2115 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.21", "pid": 2338710, "tid": 2379450, + "ts": 6410531858158.757, "dur": 724.375, + "args": { + "External id": 1409605,"Record function id": 0, "Ev Idx": 2116 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410531858179.455, "dur": 689.421, + "args": { + "External id": 1409606,"Record function id": 0, "Ev Idx": 2117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531858257.452, "dur": 7.621, + "args": { + "External id": 1409607,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531858283.556, "dur": 43.312, + "args": { + "External id": 1409608,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858289.424, "dur": 1.957, + "args": { + "External id": 1409609,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858296.542, "dur": 0.415, + "args": { + "External id": 1409610,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858299.126, "dur": 0.671, + "args": { + "External id": 1409611,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858301.676, "dur": 0.480, + "args": { + "External id": 1409612,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858305.495, "dur": 0.657, + "args": { + "External id": 1409613,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858307.366, "dur": 3.201, + "args": { + "External id": 1409614,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858312.584, "dur": 1.256, + "args": { + "External id": 1409615,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858315.661, "dur": 0.423, + "args": { + "External id": 1409616,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858317.495, "dur": 0.467, + "args": { + "External id": 1409617,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531858339.396, "dur": 51.516, + "args": { + "External id": 1409618,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410531858447.226, "dur": 142.866, + "args": { + "External id": 1409619,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531858460.241, "dur": 5.552, + "args": { + "External id": 1409620,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410531858472.285, "dur": 12.500, + "args": { + "External id": 1409621,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531858476.916, "dur": 7.371, + "args": { + "External id": 1409622,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858481.421, "dur": 0.862, + "args": { + "External id": 1409623,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531858493.223, "dur": 36.045, + "args": { + "External id": 1409624,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858495.948, "dur": 2.410, + "args": { + "External id": 1409625,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858500.411, "dur": 0.594, + "args": { + "External id": 1409626,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858503.025, "dur": 2.627, + "args": { + "External id": 1409627,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858509.103, "dur": 0.350, + "args": { + "External id": 1409628,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858511.090, "dur": 0.300, + "args": { + "External id": 1409629,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858513.074, "dur": 0.525, + "args": { + "External id": 1409630,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858516.578, "dur": 0.357, + "args": { + "External id": 1409631,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858518.759, "dur": 0.401, + "args": { + "External id": 1409632,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531858520.744, "dur": 1.631, + "args": { + "External id": 1409633,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531858543.875, "dur": 36.326, + "args": { + "External id": 1409634,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531858644.298, "dur": 142.717, + "args": { + "External id": 1409635,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531858678.395, "dur": 104.471, + "args": { + "External id": 1409636,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2147, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531858691.637, "dur": 86.117, + "args": { + "External id": 1409637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531858807.277, "dur": 2.429, + "args": { + "External id": 1409638,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2149, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531858900.516, "dur": 2097.537, + "args": { + "External id": 1409639,"Sequence number": 15108888, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2150 + } + }, + { + "ph": "f", "id": 178, "pid": 2338710, "tid": 2379450, "ts": 6410531858900.516, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531859030.823, "dur": 167.154, + "args": { + "External id": 1409640,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531859254.916, "dur": 48.122, + "args": { + "External id": 1409641,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531859324.772, "dur": 58.326, + "args": { + "External id": 1409642,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531859409.724, "dur": 59.654, + "args": { + "External id": 1409643,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531859481.090, "dur": 38.035, + "args": { + "External id": 1409644,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531859526.681, "dur": 30.410, + "args": { + "External id": 1409645,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531859566.878, "dur": 31.900, + "args": { + "External id": 1409646,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531859635.359, "dur": 29.958, + "args": { + "External id": 1409647,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531859689.366, "dur": 31.612, + "args": { + "External id": 1409648,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531859747.845, "dur": 24.512, + "args": { + "External id": 1409649,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531859788.248, "dur": 15.804, + "args": { + "External id": 1409650,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531859815.079, "dur": 40.319, + "args": { + "External id": 1409651,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531859859.112, "dur": 34.846, + "args": { + "External id": 1409652,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531859938.912, "dur": 355.004, + "args": { + "External id": 1409653,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531860042.003, "dur": 11.423, + "args": { + "External id": 1409654,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531860093.183, "dur": 6.551, + "args": { + "External id": 1409655,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531860105.659, "dur": 4.341, + "args": { + "External id": 1409656,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531860111.507, "dur": 1.977, + "args": { + "External id": 1409657,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531860169.308, "dur": 8.170, + "args": { + "External id": 1409658,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531860173.644, "dur": 3.535, + "args": { + "External id": 1409659,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531860179.873, "dur": 39.788, + "args": { + "External id": 1409660,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531860186.176, "dur": 4.596, + "args": { + "External id": 1409661,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531860221.410, "dur": 1.975, + "args": { + "External id": 1409662,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531860222.601, "dur": 0.699, + "args": { + "External id": 1409663,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531860224.546, "dur": 16.033, + "args": { + "External id": 1409664,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531860226.854, "dur": 1.016, + "args": { + "External id": 1409665,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531860342.528, "dur": 34.193, + "args": { + "External id": 1409666,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531860399.498, "dur": 35.888, + "args": { + "External id": 1409667,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531860449.235, "dur": 63.439, + "args": { + "External id": 1409668,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531860521.692, "dur": 47.199, + "args": { + "External id": 1409669,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531860581.124, "dur": 24.894, + "args": { + "External id": 1409670,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531860612.880, "dur": 36.365, + "args": { + "External id": 1409671,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531860657.740, "dur": 30.461, + "args": { + "External id": 1409672,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531860698.376, "dur": 34.097, + "args": { + "External id": 1409673,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410531860758.300, "dur": 33.251, + "args": { + "External id": 1409674,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531860813.700, "dur": 29.554, + "args": { + "External id": 1409675,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531860863.645, "dur": 20.942, + "args": { + "External id": 1409676,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531860907.513, "dur": 18.755, + "args": { + "External id": 1409677,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410531860943.329, "dur": 18.661, + "args": { + "External id": 1409678,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861051.263, "dur": 58.487, + "args": { + "External id": 1409679,"Record function id": 0, "Ev Idx": 2190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861093.025, "dur": 15.038, + "args": { + "External id": 1409680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861099.403, "dur": 6.875, + "args": { + "External id": 1409681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861101.168, "dur": 4.768, + "args": { + "External id": 1409682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861117.250, "dur": 6.493, + "args": { + "External id": 1409683,"Record function id": 0, "Ev Idx": 2194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861119.832, "dur": 3.436, + "args": { + "External id": 1409684,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861120.801, "dur": 1.818, + "args": { + "External id": 1409685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861121.293, "dur": 1.222, + "args": { + "External id": 1409686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861127.688, "dur": 8.306, + "args": { + "External id": 1409687,"Record function id": 0, "Ev Idx": 2198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861129.366, "dur": 6.035, + "args": { + "External id": 1409688,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861130.419, "dur": 4.489, + "args": { + "External id": 1409689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861131.238, "dur": 3.549, + "args": { + "External id": 1409690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861140.032, "dur": 5.446, + "args": { + "External id": 1409691,"Record function id": 0, "Ev Idx": 2202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861141.914, "dur": 3.108, + "args": { + "External id": 1409692,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861142.690, "dur": 1.833, + "args": { + "External id": 1409693,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861143.314, "dur": 1.115, + "args": { + "External id": 1409694,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861149.241, "dur": 4.539, + "args": { + "External id": 1409695,"Record function id": 0, "Ev Idx": 2206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861150.671, "dur": 2.650, + "args": { + "External id": 1409696,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861151.449, "dur": 1.365, + "args": { + "External id": 1409697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861151.867, "dur": 0.823, + "args": { + "External id": 1409698,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861157.518, "dur": 4.886, + "args": { + "External id": 1409699,"Record function id": 0, "Ev Idx": 2210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861159.127, "dur": 2.816, + "args": { + "External id": 1409700,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861159.828, "dur": 1.514, + "args": { + "External id": 1409701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861160.537, "dur": 0.721, + "args": { + "External id": 1409702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861166.121, "dur": 4.754, + "args": { + "External id": 1409703,"Record function id": 0, "Ev Idx": 2214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861167.579, "dur": 2.794, + "args": { + "External id": 1409704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861168.436, "dur": 1.461, + "args": { + "External id": 1409705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861168.923, "dur": 0.851, + "args": { + "External id": 1409706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861174.506, "dur": 6.993, + "args": { + "External id": 1409707,"Record function id": 0, "Ev Idx": 2218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861176.190, "dur": 4.812, + "args": { + "External id": 1409708,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861176.734, "dur": 3.683, + "args": { + "External id": 1409709,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861179.580, "dur": 0.758, + "args": { + "External id": 1409710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861187.021, "dur": 4.731, + "args": { + "External id": 1409711,"Record function id": 0, "Ev Idx": 2222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531861188.563, "dur": 2.708, + "args": { + "External id": 1409712,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861189.332, "dur": 1.347, + "args": { + "External id": 1409713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531861189.684, "dur": 0.869, + "args": { + "External id": 1409714,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531861196.530, "dur": 67671.231, + "args": { + "External id": 1409715,"Record function id": 0, "Sequence number": 15108887, "Fwd thread id": 1, "Ev Idx": 2226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531861198.194, "dur": 67659.093, + "args": { + "External id": 1409716,"Sequence number": 15108887, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2227 + } + }, + { + "ph": "f", "id": 179, "pid": 2338710, "tid": 2379450, "ts": 6410531861198.194, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410531861232.346, "dur": 49.044, + "args": { + "External id": 1409717,"Record function id": 0, "Ev Idx": 2228 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410531861291.391, "dur": 76.957, + "args": { + "External id": 1409718,"Record function id": 0, "Ev Idx": 2229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410531861375.553, "dur": 67472.647, + "args": { + "External id": 1409719,"Record function id": 0, "Ev Idx": 2230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531861498.424, "dur": 8.522, + "args": { + "External id": 1409720,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531861519.853, "dur": 7.964, + "args": { + "External id": 1409721,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531861549.927, "dur": 66261.143, + "args": { + "External id": 1409722,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531861568.296, "dur": 66227.047, + "args": { + "External id": 1409723,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531861692.587, "dur": 23.260, + "args": { + "External id": 1409724,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531861741.907, "dur": 65994.533, + "args": { + "External id": 1409725,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531861745.333, "dur": 65989.561, + "args": { + "External id": 1409726,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531861750.624, "dur": 13.992, + "args": { + "External id": 1409727,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531861767.299, "dur": 65961.766, + "args": { + "External id": 1409728,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531927937.905, "dur": 16.644, + "args": { + "External id": 1409729,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531927942.814, "dur": 11.383, + "args": { + "External id": 1409730,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531927990.223, "dur": 489.546, + "args": { + "External id": 1409731,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531928028.443, "dur": 445.296, + "args": { + "External id": 1409732,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2243, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531928045.573, "dur": 420.269, + "args": { + "External id": 1409733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531928510.956, "dur": 2.959, + "args": { + "External id": 1409734,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2245, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928589.500, "dur": 7.790, + "args": { + "External id": 1409735,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928652.346, "dur": 1.531, + "args": { + "External id": 1409736,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928673.820, "dur": 4.126, + "args": { + "External id": 1409737,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928694.175, "dur": 1.160, + "args": { + "External id": 1409738,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928711.069, "dur": 1.264, + "args": { + "External id": 1409739,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928724.736, "dur": 1.041, + "args": { + "External id": 1409740,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928738.505, "dur": 3.184, + "args": { + "External id": 1409741,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928755.110, "dur": 3.550, + "args": { + "External id": 1409742,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531928773.983, "dur": 0.975, + "args": { + "External id": 1409743,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531928884.628, "dur": 3509.638, + "args": { + "External id": 1409744,"Record function id": 0, "Ev Idx": 2255 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410531928908.570, "dur": 1350.230, + "args": { + "External id": 1409745,"Record function id": 0, "Ev Idx": 2256 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410531928925.380, "dur": 447.025, + "args": { + "External id": 1409746,"Record function id": 0, "Ev Idx": 2257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929033.827, "dur": 5.431, + "args": { + "External id": 1409747,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929043.260, "dur": 1.391, + "args": { + "External id": 1409748,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929046.677, "dur": 3.592, + "args": { + "External id": 1409749,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929093.054, "dur": 1.891, + "args": { + "External id": 1409750,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929099.208, "dur": 0.948, + "args": { + "External id": 1409751,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929102.124, "dur": 1.130, + "args": { + "External id": 1409752,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929105.174, "dur": 2.991, + "args": { + "External id": 1409753,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929112.790, "dur": 1.076, + "args": { + "External id": 1409754,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929115.918, "dur": 0.912, + "args": { + "External id": 1409755,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531929119.057, "dur": 0.867, + "args": { + "External id": 1409756,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531929141.699, "dur": 191.103, + "args": { + "External id": 1409757,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531929161.445, "dur": 165.802, + "args": { + "External id": 1409758,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531929187.574, "dur": 17.306, + "args": { + "External id": 1409759,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531929211.611, "dur": 81.422, + "args": { + "External id": 1409760,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531929214.698, "dur": 77.852, + "args": { + "External id": 1409761,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929221.127, "dur": 7.892, + "args": { + "External id": 1409762,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531929231.045, "dur": 60.753, + "args": { + "External id": 1409763,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2274 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.20", "pid": 2338710, "tid": 2379450, + "ts": 6410531929505.080, "dur": 744.453, + "args": { + "External id": 1409764,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410531929526.822, "dur": 707.812, + "args": { + "External id": 1409765,"Record function id": 0, "Ev Idx": 2276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531929603.159, "dur": 7.586, + "args": { + "External id": 1409766,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531929629.887, "dur": 42.364, + "args": { + "External id": 1409767,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929635.891, "dur": 2.158, + "args": { + "External id": 1409768,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929640.333, "dur": 2.575, + "args": { + "External id": 1409769,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929644.679, "dur": 0.473, + "args": { + "External id": 1409770,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929646.863, "dur": 0.359, + "args": { + "External id": 1409771,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929651.180, "dur": 0.363, + "args": { + "External id": 1409772,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929653.061, "dur": 2.314, + "args": { + "External id": 1409773,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929656.943, "dur": 0.630, + "args": { + "External id": 1409774,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929660.808, "dur": 0.414, + "args": { + "External id": 1409775,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929663.040, "dur": 0.658, + "args": { + "External id": 1409776,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531929684.152, "dur": 50.505, + "args": { + "External id": 1409777,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410531929772.161, "dur": 131.129, + "args": { + "External id": 1409778,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531929784.685, "dur": 4.756, + "args": { + "External id": 1409779,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410531929795.577, "dur": 12.000, + "args": { + "External id": 1409780,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531929800.366, "dur": 6.744, + "args": { + "External id": 1409781,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929804.800, "dur": 0.722, + "args": { + "External id": 1409782,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531929814.728, "dur": 35.897, + "args": { + "External id": 1409783,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929817.345, "dur": 0.526, + "args": { + "External id": 1409784,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929821.936, "dur": 0.311, + "args": { + "External id": 1409785,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929823.858, "dur": 2.573, + "args": { + "External id": 1409786,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929828.152, "dur": 2.889, + "args": { + "External id": 1409787,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929832.689, "dur": 0.378, + "args": { + "External id": 1409788,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929834.747, "dur": 0.643, + "args": { + "External id": 1409789,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929839.349, "dur": 0.321, + "args": { + "External id": 1409790,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929840.955, "dur": 0.347, + "args": { + "External id": 1409791,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531929842.790, "dur": 0.286, + "args": { + "External id": 1409792,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531929862.704, "dur": 31.668, + "args": { + "External id": 1409793,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531929955.996, "dur": 184.085, + "args": { + "External id": 1409794,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531929988.344, "dur": 146.571, + "args": { + "External id": 1409795,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2306, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531929999.018, "dur": 130.006, + "args": { + "External id": 1409796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531930166.494, "dur": 2.255, + "args": { + "External id": 1409797,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2308, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531930268.261, "dur": 2096.847, + "args": { + "External id": 1409798,"Sequence number": 15108886, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2309 + } + }, + { + "ph": "f", "id": 180, "pid": 2338710, "tid": 2379450, "ts": 6410531930268.261, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531930400.485, "dur": 143.016, + "args": { + "External id": 1409799,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531930597.477, "dur": 48.028, + "args": { + "External id": 1409800,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531930668.070, "dur": 60.698, + "args": { + "External id": 1409801,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531930742.584, "dur": 36.453, + "args": { + "External id": 1409802,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531930786.040, "dur": 36.865, + "args": { + "External id": 1409803,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531930830.962, "dur": 30.648, + "args": { + "External id": 1409804,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531930870.336, "dur": 33.701, + "args": { + "External id": 1409805,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531930936.891, "dur": 27.485, + "args": { + "External id": 1409806,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531930986.758, "dur": 31.538, + "args": { + "External id": 1409807,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531931045.331, "dur": 63.974, + "args": { + "External id": 1409808,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531931129.922, "dur": 21.330, + "args": { + "External id": 1409809,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531931161.717, "dur": 49.881, + "args": { + "External id": 1409810,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531931215.729, "dur": 36.782, + "args": { + "External id": 1409811,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531931289.612, "dur": 355.810, + "args": { + "External id": 1409812,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531931388.945, "dur": 7.121, + "args": { + "External id": 1409813,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531931398.477, "dur": 2.721, + "args": { + "External id": 1409814,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531931402.684, "dur": 3.176, + "args": { + "External id": 1409815,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531931407.093, "dur": 1.758, + "args": { + "External id": 1409816,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531931497.289, "dur": 7.223, + "args": { + "External id": 1409817,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531931499.691, "dur": 3.930, + "args": { + "External id": 1409818,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531931509.369, "dur": 46.873, + "args": { + "External id": 1409819,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531931516.717, "dur": 6.610, + "args": { + "External id": 1409820,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410531931558.262, "dur": 1.979, + "args": { + "External id": 1409821,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531931559.455, "dur": 0.676, + "args": { + "External id": 1409822,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410531931561.769, "dur": 18.033, + "args": { + "External id": 1409823,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531931563.918, "dur": 0.541, + "args": { + "External id": 1409824,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531931693.266, "dur": 36.541, + "args": { + "External id": 1409825,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531931751.645, "dur": 20.287, + "args": { + "External id": 1409826,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531931781.438, "dur": 58.592, + "args": { + "External id": 1409827,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531931847.819, "dur": 47.014, + "args": { + "External id": 1409828,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531931906.216, "dur": 25.360, + "args": { + "External id": 1409829,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531931938.941, "dur": 35.725, + "args": { + "External id": 1409830,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531931983.382, "dur": 30.969, + "args": { + "External id": 1409831,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531932021.786, "dur": 33.211, + "args": { + "External id": 1409832,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410531932123.442, "dur": 32.972, + "args": { + "External id": 1409833,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531932188.046, "dur": 28.741, + "args": { + "External id": 1409834,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531932239.818, "dur": 19.062, + "args": { + "External id": 1409835,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531932280.444, "dur": 15.401, + "args": { + "External id": 1409836,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410531932315.393, "dur": 17.372, + "args": { + "External id": 1409837,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932434.310, "dur": 22.020, + "args": { + "External id": 1409838,"Record function id": 0, "Ev Idx": 2349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932439.613, "dur": 15.326, + "args": { + "External id": 1409839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932444.425, "dur": 9.001, + "args": { + "External id": 1409840,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932446.287, "dur": 6.825, + "args": { + "External id": 1409841,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932462.467, "dur": 6.048, + "args": { + "External id": 1409842,"Record function id": 0, "Ev Idx": 2353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932464.195, "dur": 3.734, + "args": { + "External id": 1409843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932464.975, "dur": 2.042, + "args": { + "External id": 1409844,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932465.696, "dur": 1.188, + "args": { + "External id": 1409845,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932472.407, "dur": 7.820, + "args": { + "External id": 1409846,"Record function id": 0, "Ev Idx": 2357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932474.428, "dur": 5.269, + "args": { + "External id": 1409847,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932475.078, "dur": 4.137, + "args": { + "External id": 1409848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932476.147, "dur": 2.924, + "args": { + "External id": 1409849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932484.138, "dur": 5.284, + "args": { + "External id": 1409850,"Record function id": 0, "Ev Idx": 2361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932485.807, "dur": 3.084, + "args": { + "External id": 1409851,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932487.052, "dur": 1.299, + "args": { + "External id": 1409852,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932487.394, "dur": 0.851, + "args": { + "External id": 1409853,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932493.157, "dur": 4.718, + "args": { + "External id": 1409854,"Record function id": 0, "Ev Idx": 2365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932494.734, "dur": 2.662, + "args": { + "External id": 1409855,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932495.525, "dur": 1.396, + "args": { + "External id": 1409856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932496.072, "dur": 0.771, + "args": { + "External id": 1409857,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932501.565, "dur": 4.962, + "args": { + "External id": 1409858,"Record function id": 0, "Ev Idx": 2369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932503.161, "dur": 2.875, + "args": { + "External id": 1409859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932503.858, "dur": 1.587, + "args": { + "External id": 1409860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932504.361, "dur": 1.006, + "args": { + "External id": 1409861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932510.229, "dur": 5.166, + "args": { + "External id": 1409862,"Record function id": 0, "Ev Idx": 2373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932512.018, "dur": 2.893, + "args": { + "External id": 1409863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932512.665, "dur": 1.770, + "args": { + "External id": 1409864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932513.547, "dur": 0.770, + "args": { + "External id": 1409865,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932519.193, "dur": 4.215, + "args": { + "External id": 1409866,"Record function id": 0, "Ev Idx": 2377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932520.517, "dur": 2.378, + "args": { + "External id": 1409867,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932521.261, "dur": 1.146, + "args": { + "External id": 1409868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932521.603, "dur": 0.716, + "args": { + "External id": 1409869,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932528.419, "dur": 7.421, + "args": { + "External id": 1409870,"Record function id": 0, "Ev Idx": 2381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410531932529.847, "dur": 5.503, + "args": { + "External id": 1409871,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932530.408, "dur": 4.131, + "args": { + "External id": 1409872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410531932533.719, "dur": 0.729, + "args": { + "External id": 1409873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531932541.110, "dur": 65052.068, + "args": { + "External id": 1409874,"Record function id": 0, "Sequence number": 15108885, "Fwd thread id": 1, "Ev Idx": 2385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531932542.650, "dur": 65040.268, + "args": { + "External id": 1409875,"Sequence number": 15108885, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2386 + } + }, + { + "ph": "f", "id": 181, "pid": 2338710, "tid": 2379450, "ts": 6410531932542.650, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410531932581.458, "dur": 46.308, + "args": { + "External id": 1409876,"Record function id": 0, "Ev Idx": 2387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410531932637.167, "dur": 70.625, + "args": { + "External id": 1409877,"Record function id": 0, "Ev Idx": 2388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410531932716.842, "dur": 64856.660, + "args": { + "External id": 1409878,"Record function id": 0, "Ev Idx": 2389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531932822.027, "dur": 8.845, + "args": { + "External id": 1409879,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531932842.182, "dur": 6.884, + "args": { + "External id": 1409880,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531932866.163, "dur": 63589.045, + "args": { + "External id": 1409881,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410531932885.370, "dur": 63554.047, + "args": { + "External id": 1409882,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531932988.668, "dur": 20.460, + "args": { + "External id": 1409883,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531933032.475, "dur": 63335.815, + "args": { + "External id": 1409884,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531933035.556, "dur": 63331.169, + "args": { + "External id": 1409885,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531933041.048, "dur": 12.566, + "args": { + "External id": 1409886,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531933103.121, "dur": 63255.762, + "args": { + "External id": 1409887,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531996586.229, "dur": 16.073, + "args": { + "External id": 1409888,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531996590.888, "dur": 11.039, + "args": { + "External id": 1409889,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531996638.766, "dur": 529.064, + "args": { + "External id": 1409890,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531996677.840, "dur": 482.898, + "args": { + "External id": 1409891,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2402, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531996693.880, "dur": 459.876, + "args": { + "External id": 1409892,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531997209.224, "dur": 2.877, + "args": { + "External id": 1409893,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2404, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997288.023, "dur": 8.206, + "args": { + "External id": 1409894,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997351.484, "dur": 1.454, + "args": { + "External id": 1409895,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997371.879, "dur": 4.110, + "args": { + "External id": 1409896,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997390.192, "dur": 0.996, + "args": { + "External id": 1409897,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997408.328, "dur": 1.057, + "args": { + "External id": 1409898,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997444.250, "dur": 1.818, + "args": { + "External id": 1409899,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997460.323, "dur": 3.210, + "args": { + "External id": 1409900,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997477.391, "dur": 3.640, + "args": { + "External id": 1409901,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997495.029, "dur": 1.146, + "args": { + "External id": 1409902,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531997615.668, "dur": 4072.574, + "args": { + "External id": 1409903,"Record function id": 0, "Ev Idx": 2414 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410531997640.537, "dur": 1317.400, + "args": { + "External id": 1409904,"Record function id": 0, "Ev Idx": 2415 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410531997660.472, "dur": 391.467, + "args": { + "External id": 1409905,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997772.128, "dur": 4.901, + "args": { + "External id": 1409906,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997780.854, "dur": 1.220, + "args": { + "External id": 1409907,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997784.399, "dur": 3.173, + "args": { + "External id": 1409908,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997790.139, "dur": 0.953, + "args": { + "External id": 1409909,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997793.288, "dur": 1.280, + "args": { + "External id": 1409910,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997796.793, "dur": 1.260, + "args": { + "External id": 1409911,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997799.935, "dur": 3.664, + "args": { + "External id": 1409912,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997807.697, "dur": 1.080, + "args": { + "External id": 1409913,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997810.422, "dur": 1.016, + "args": { + "External id": 1409914,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410531997813.259, "dur": 1.061, + "args": { + "External id": 1409915,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531997835.094, "dur": 180.681, + "args": { + "External id": 1409916,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531997854.182, "dur": 155.966, + "args": { + "External id": 1409917,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531997878.888, "dur": 17.470, + "args": { + "External id": 1409918,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410531997901.188, "dur": 77.441, + "args": { + "External id": 1409919,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410531997903.989, "dur": 74.228, + "args": { + "External id": 1409920,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531997908.618, "dur": 6.849, + "args": { + "External id": 1409921,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531997917.762, "dur": 59.833, + "args": { + "External id": 1409922,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2433 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.19", "pid": 2338710, "tid": 2379450, + "ts": 6410531998213.303, "dur": 735.857, + "args": { + "External id": 1409923,"Record function id": 0, "Ev Idx": 2434 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410531998235.205, "dur": 699.422, + "args": { + "External id": 1409924,"Record function id": 0, "Ev Idx": 2435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531998309.342, "dur": 7.236, + "args": { + "External id": 1409925,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531998335.134, "dur": 45.832, + "args": { + "External id": 1409926,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998341.339, "dur": 3.844, + "args": { + "External id": 1409927,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998347.714, "dur": 0.804, + "args": { + "External id": 1409928,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998350.367, "dur": 0.421, + "args": { + "External id": 1409929,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998355.055, "dur": 0.449, + "args": { + "External id": 1409930,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998357.082, "dur": 0.739, + "args": { + "External id": 1409931,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998359.703, "dur": 3.023, + "args": { + "External id": 1409932,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998365.649, "dur": 0.655, + "args": { + "External id": 1409933,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998367.919, "dur": 0.537, + "args": { + "External id": 1409934,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998370.138, "dur": 2.843, + "args": { + "External id": 1409935,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531998393.522, "dur": 72.164, + "args": { + "External id": 1409936,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410531998511.385, "dur": 142.865, + "args": { + "External id": 1409937,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410531998524.970, "dur": 4.983, + "args": { + "External id": 1409938,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410531998539.715, "dur": 12.987, + "args": { + "External id": 1409939,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410531998544.495, "dur": 7.725, + "args": { + "External id": 1409940,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998549.177, "dur": 0.943, + "args": { + "External id": 1409941,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410531998561.524, "dur": 34.682, + "args": { + "External id": 1409942,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998564.307, "dur": 0.501, + "args": { + "External id": 1409943,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998567.231, "dur": 0.467, + "args": { + "External id": 1409944,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998569.294, "dur": 3.638, + "args": { + "External id": 1409945,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998574.644, "dur": 0.486, + "args": { + "External id": 1409946,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998576.633, "dur": 0.428, + "args": { + "External id": 1409947,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998580.402, "dur": 0.529, + "args": { + "External id": 1409948,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998582.693, "dur": 0.659, + "args": { + "External id": 1409949,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998585.003, "dur": 0.649, + "args": { + "External id": 1409950,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410531998588.333, "dur": 0.355, + "args": { + "External id": 1409951,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410531998612.043, "dur": 32.724, + "args": { + "External id": 1409952,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410531998709.777, "dur": 141.597, + "args": { + "External id": 1409953,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531998744.220, "dur": 102.787, + "args": { + "External id": 1409954,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2465, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410531998757.419, "dur": 84.616, + "args": { + "External id": 1409955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410531998871.636, "dur": 2.077, + "args": { + "External id": 1409956,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2467, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410531998966.403, "dur": 2496.609, + "args": { + "External id": 1409957,"Sequence number": 15108884, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2468 + } + }, + { + "ph": "f", "id": 182, "pid": 2338710, "tid": 2379450, "ts": 6410531998966.403, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531999142.361, "dur": 132.687, + "args": { + "External id": 1409958,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531999325.021, "dur": 48.240, + "args": { + "External id": 1409959,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410531999392.916, "dur": 76.282, + "args": { + "External id": 1409960,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531999488.052, "dur": 38.671, + "args": { + "External id": 1409961,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531999534.569, "dur": 35.849, + "args": { + "External id": 1409962,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531999577.898, "dur": 31.760, + "args": { + "External id": 1409963,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531999618.934, "dur": 33.362, + "args": { + "External id": 1409964,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410531999686.499, "dur": 29.193, + "args": { + "External id": 1409965,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410531999740.324, "dur": 32.163, + "args": { + "External id": 1409966,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410531999800.168, "dur": 23.200, + "args": { + "External id": 1409967,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410531999841.442, "dur": 17.214, + "args": { + "External id": 1409968,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531999866.959, "dur": 44.073, + "args": { + "External id": 1409969,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410531999914.815, "dur": 37.052, + "args": { + "External id": 1409970,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410531999989.202, "dur": 378.364, + "args": { + "External id": 1409971,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532000148.459, "dur": 9.867, + "args": { + "External id": 1409972,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532000161.283, "dur": 4.191, + "args": { + "External id": 1409973,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532000166.806, "dur": 6.189, + "args": { + "External id": 1409974,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532000174.159, "dur": 2.436, + "args": { + "External id": 1409975,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532000238.000, "dur": 9.824, + "args": { + "External id": 1409976,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532000244.417, "dur": 3.203, + "args": { + "External id": 1409977,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532000250.243, "dur": 40.613, + "args": { + "External id": 1409978,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532000256.469, "dur": 4.222, + "args": { + "External id": 1409979,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532000292.585, "dur": 2.340, + "args": { + "External id": 1409980,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532000293.754, "dur": 1.050, + "args": { + "External id": 1409981,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532000296.453, "dur": 17.115, + "args": { + "External id": 1409982,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532000298.453, "dur": 0.527, + "args": { + "External id": 1409983,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532000413.808, "dur": 53.571, + "args": { + "External id": 1409984,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532000494.417, "dur": 20.327, + "args": { + "External id": 1409985,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532000525.024, "dur": 63.051, + "args": { + "External id": 1409986,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532000595.805, "dur": 47.478, + "args": { + "External id": 1409987,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532000654.594, "dur": 27.534, + "args": { + "External id": 1409988,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532000689.243, "dur": 35.840, + "args": { + "External id": 1409989,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532000733.113, "dur": 32.186, + "args": { + "External id": 1409990,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532000773.531, "dur": 35.377, + "args": { + "External id": 1409991,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532000842.249, "dur": 39.849, + "args": { + "External id": 1409992,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532000933.402, "dur": 39.603, + "args": { + "External id": 1409993,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532001003.612, "dur": 27.458, + "args": { + "External id": 1409994,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532001107.715, "dur": 35.515, + "args": { + "External id": 1409995,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532001174.823, "dur": 25.830, + "args": { + "External id": 1409996,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001719.984, "dur": 37.225, + "args": { + "External id": 1409997,"Record function id": 0, "Ev Idx": 2508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001726.368, "dur": 27.148, + "args": { + "External id": 1409998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001733.011, "dur": 16.870, + "args": { + "External id": 1409999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001735.095, "dur": 12.767, + "args": { + "External id": 1410000,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001768.443, "dur": 10.170, + "args": { + "External id": 1410001,"Record function id": 0, "Ev Idx": 2512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001772.199, "dur": 5.569, + "args": { + "External id": 1410002,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001774.009, "dur": 2.926, + "args": { + "External id": 1410003,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001775.016, "dur": 1.755, + "args": { + "External id": 1410004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001784.469, "dur": 9.662, + "args": { + "External id": 1410005,"Record function id": 0, "Ev Idx": 2516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001786.385, "dur": 7.229, + "args": { + "External id": 1410006,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001787.658, "dur": 5.413, + "args": { + "External id": 1410007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001789.059, "dur": 3.876, + "args": { + "External id": 1410008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001801.309, "dur": 5.407, + "args": { + "External id": 1410009,"Record function id": 0, "Ev Idx": 2520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001803.122, "dur": 3.110, + "args": { + "External id": 1410010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001804.011, "dur": 1.628, + "args": { + "External id": 1410011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001804.488, "dur": 1.056, + "args": { + "External id": 1410012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001810.731, "dur": 5.036, + "args": { + "External id": 1410013,"Record function id": 0, "Ev Idx": 2524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001812.325, "dur": 2.967, + "args": { + "External id": 1410014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001813.218, "dur": 1.554, + "args": { + "External id": 1410015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001813.733, "dur": 0.958, + "args": { + "External id": 1410016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001819.569, "dur": 6.186, + "args": { + "External id": 1410017,"Record function id": 0, "Ev Idx": 2528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001821.498, "dur": 3.791, + "args": { + "External id": 1410018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001822.608, "dur": 2.191, + "args": { + "External id": 1410019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001823.655, "dur": 1.056, + "args": { + "External id": 1410020,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001829.615, "dur": 5.603, + "args": { + "External id": 1410021,"Record function id": 0, "Ev Idx": 2532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001831.841, "dur": 2.874, + "args": { + "External id": 1410022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001832.828, "dur": 1.323, + "args": { + "External id": 1410023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001833.328, "dur": 0.701, + "args": { + "External id": 1410024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001838.983, "dur": 7.467, + "args": { + "External id": 1410025,"Record function id": 0, "Ev Idx": 2536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001840.899, "dur": 5.062, + "args": { + "External id": 1410026,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001841.662, "dur": 3.665, + "args": { + "External id": 1410027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001844.363, "dur": 0.888, + "args": { + "External id": 1410028,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001850.313, "dur": 8.123, + "args": { + "External id": 1410029,"Record function id": 0, "Ev Idx": 2540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532001852.014, "dur": 5.923, + "args": { + "External id": 1410030,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001852.680, "dur": 4.785, + "args": { + "External id": 1410031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532001853.318, "dur": 4.032, + "args": { + "External id": 1410032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532001863.582, "dur": 61293.039, + "args": { + "External id": 1410033,"Record function id": 0, "Sequence number": 15108883, "Fwd thread id": 1, "Ev Idx": 2544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532001865.249, "dur": 61280.074, + "args": { + "External id": 1410034,"Sequence number": 15108883, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2545 + } + }, + { + "ph": "f", "id": 183, "pid": 2338710, "tid": 2379450, "ts": 6410532001865.249, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410532001907.921, "dur": 50.936, + "args": { + "External id": 1410035,"Record function id": 0, "Ev Idx": 2546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410532001969.256, "dur": 82.380, + "args": { + "External id": 1410036,"Record function id": 0, "Ev Idx": 2547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410532002094.826, "dur": 61039.830, + "args": { + "External id": 1410037,"Record function id": 0, "Ev Idx": 2548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532002211.315, "dur": 10.767, + "args": { + "External id": 1410038,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532002235.099, "dur": 8.548, + "args": { + "External id": 1410039,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532002260.775, "dur": 59779.239, + "args": { + "External id": 1410040,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532002280.214, "dur": 59745.040, + "args": { + "External id": 1410041,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532002382.323, "dur": 21.374, + "args": { + "External id": 1410042,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532002448.849, "dur": 59518.753, + "args": { + "External id": 1410043,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532002454.950, "dur": 59511.505, + "args": { + "External id": 1410044,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532002463.043, "dur": 14.192, + "args": { + "External id": 1410045,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532002481.897, "dur": 59479.151, + "args": { + "External id": 1410046,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532062197.087, "dur": 15.787, + "args": { + "External id": 1410047,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532062201.281, "dur": 10.881, + "args": { + "External id": 1410048,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532062276.074, "dur": 439.267, + "args": { + "External id": 1410049,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532062314.650, "dur": 394.425, + "args": { + "External id": 1410050,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2561, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532062329.977, "dur": 372.380, + "args": { + "External id": 1410051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532062744.739, "dur": 2.703, + "args": { + "External id": 1410052,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2563, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532062831.251, "dur": 7.824, + "args": { + "External id": 1410053,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532062897.345, "dur": 1.708, + "args": { + "External id": 1410054,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532062919.246, "dur": 5.973, + "args": { + "External id": 1410055,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532062941.466, "dur": 1.210, + "args": { + "External id": 1410056,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532062959.375, "dur": 0.956, + "args": { + "External id": 1410057,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532062974.137, "dur": 1.308, + "args": { + "External id": 1410058,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532062988.199, "dur": 3.250, + "args": { + "External id": 1410059,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063004.936, "dur": 3.559, + "args": { + "External id": 1410060,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063020.908, "dur": 2.507, + "args": { + "External id": 1410061,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532063176.531, "dur": 3493.016, + "args": { + "External id": 1410062,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410532063202.034, "dur": 1351.962, + "args": { + "External id": 1410063,"Record function id": 0, "Ev Idx": 2574 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410532063220.769, "dur": 430.061, + "args": { + "External id": 1410064,"Record function id": 0, "Ev Idx": 2575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063338.950, "dur": 5.314, + "args": { + "External id": 1410065,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063348.223, "dur": 1.164, + "args": { + "External id": 1410066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063351.675, "dur": 3.425, + "args": { + "External id": 1410067,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063357.395, "dur": 1.436, + "args": { + "External id": 1410068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063360.489, "dur": 1.190, + "args": { + "External id": 1410069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063363.443, "dur": 1.054, + "args": { + "External id": 1410070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063369.584, "dur": 3.706, + "args": { + "External id": 1410071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063377.571, "dur": 1.346, + "args": { + "External id": 1410072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063380.694, "dur": 1.134, + "args": { + "External id": 1410073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532063383.613, "dur": 0.995, + "args": { + "External id": 1410074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532063404.951, "dur": 205.605, + "args": { + "External id": 1410075,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532063442.246, "dur": 162.391, + "args": { + "External id": 1410076,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532063464.280, "dur": 19.308, + "args": { + "External id": 1410077,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532063490.710, "dur": 80.349, + "args": { + "External id": 1410078,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532063493.715, "dur": 76.792, + "args": { + "External id": 1410079,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063498.944, "dur": 7.339, + "args": { + "External id": 1410080,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532063508.041, "dur": 61.794, + "args": { + "External id": 1410081,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2592 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.18", "pid": 2338710, "tid": 2379450, + "ts": 6410532063761.231, "dur": 783.571, + "args": { + "External id": 1410082,"Record function id": 0, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410532063780.879, "dur": 749.269, + "args": { + "External id": 1410083,"Record function id": 0, "Ev Idx": 2594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532063852.385, "dur": 5.474, + "args": { + "External id": 1410084,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532063875.643, "dur": 40.645, + "args": { + "External id": 1410085,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063881.377, "dur": 1.786, + "args": { + "External id": 1410086,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063885.740, "dur": 1.588, + "args": { + "External id": 1410087,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063889.461, "dur": 0.436, + "args": { + "External id": 1410088,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063891.722, "dur": 0.606, + "args": { + "External id": 1410089,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063895.505, "dur": 0.559, + "args": { + "External id": 1410090,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063898.337, "dur": 2.180, + "args": { + "External id": 1410091,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063902.419, "dur": 0.572, + "args": { + "External id": 1410092,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063905.697, "dur": 0.375, + "args": { + "External id": 1410093,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532063907.759, "dur": 0.583, + "args": { + "External id": 1410094,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532063928.271, "dur": 49.152, + "args": { + "External id": 1410095,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532064014.976, "dur": 199.016, + "args": { + "External id": 1410096,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532064026.402, "dur": 3.986, + "args": { + "External id": 1410097,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532064036.214, "dur": 11.931, + "args": { + "External id": 1410098,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532064041.170, "dur": 6.511, + "args": { + "External id": 1410099,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064045.290, "dur": 0.844, + "args": { + "External id": 1410100,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532064114.904, "dur": 35.876, + "args": { + "External id": 1410101,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064118.327, "dur": 0.959, + "args": { + "External id": 1410102,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064122.731, "dur": 0.687, + "args": { + "External id": 1410103,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064125.181, "dur": 2.747, + "args": { + "External id": 1410104,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064129.400, "dur": 2.084, + "args": { + "External id": 1410105,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064133.270, "dur": 0.596, + "args": { + "External id": 1410106,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064135.417, "dur": 0.433, + "args": { + "External id": 1410107,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064138.779, "dur": 0.394, + "args": { + "External id": 1410108,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064140.978, "dur": 0.372, + "args": { + "External id": 1410109,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532064142.881, "dur": 0.464, + "args": { + "External id": 1410110,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532064166.179, "dur": 37.814, + "args": { + "External id": 1410111,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532064272.003, "dur": 141.426, + "args": { + "External id": 1410112,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532064307.014, "dur": 102.266, + "args": { + "External id": 1410113,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2624, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532064318.168, "dur": 85.955, + "args": { + "External id": 1410114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532064457.450, "dur": 3.190, + "args": { + "External id": 1410115,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2626, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532064562.756, "dur": 2076.360, + "args": { + "External id": 1410116,"Sequence number": 15108882, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2627 + } + }, + { + "ph": "f", "id": 184, "pid": 2338710, "tid": 2379450, "ts": 6410532064562.756, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532064693.189, "dur": 123.408, + "args": { + "External id": 1410117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532064865.696, "dur": 46.283, + "args": { + "External id": 1410118,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532064931.459, "dur": 60.294, + "args": { + "External id": 1410119,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532065008.897, "dur": 36.990, + "args": { + "External id": 1410120,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532065053.128, "dur": 84.001, + "args": { + "External id": 1410121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532065149.730, "dur": 34.590, + "args": { + "External id": 1410122,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532065193.938, "dur": 32.954, + "args": { + "External id": 1410123,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532065261.895, "dur": 27.482, + "args": { + "External id": 1410124,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532065310.943, "dur": 32.381, + "args": { + "External id": 1410125,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532065372.110, "dur": 21.184, + "args": { + "External id": 1410126,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532065409.180, "dur": 34.447, + "args": { + "External id": 1410127,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532065457.481, "dur": 48.909, + "args": { + "External id": 1410128,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532065510.445, "dur": 36.776, + "args": { + "External id": 1410129,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532065582.857, "dur": 325.797, + "args": { + "External id": 1410130,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532065693.288, "dur": 9.230, + "args": { + "External id": 1410131,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532065705.242, "dur": 3.232, + "args": { + "External id": 1410132,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532065709.963, "dur": 2.475, + "args": { + "External id": 1410133,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532065713.779, "dur": 2.727, + "args": { + "External id": 1410134,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532065782.047, "dur": 6.580, + "args": { + "External id": 1410135,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532065784.902, "dur": 3.466, + "args": { + "External id": 1410136,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532065791.194, "dur": 41.870, + "args": { + "External id": 1410137,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532065798.721, "dur": 4.277, + "args": { + "External id": 1410138,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532065835.034, "dur": 2.318, + "args": { + "External id": 1410139,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532065836.484, "dur": 0.780, + "args": { + "External id": 1410140,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532065838.933, "dur": 19.230, + "args": { + "External id": 1410141,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532065841.641, "dur": 0.733, + "args": { + "External id": 1410142,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532065951.633, "dur": 34.107, + "args": { + "External id": 1410143,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532066005.177, "dur": 18.722, + "args": { + "External id": 1410144,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532066035.020, "dur": 99.198, + "args": { + "External id": 1410145,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532066147.443, "dur": 53.186, + "args": { + "External id": 1410146,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532066215.085, "dur": 26.004, + "args": { + "External id": 1410147,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532066248.949, "dur": 34.920, + "args": { + "External id": 1410148,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532066293.361, "dur": 32.004, + "args": { + "External id": 1410149,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532066333.812, "dur": 35.403, + "args": { + "External id": 1410150,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532066393.153, "dur": 46.868, + "args": { + "External id": 1410151,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532066462.387, "dur": 31.454, + "args": { + "External id": 1410152,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532066511.540, "dur": 20.859, + "args": { + "External id": 1410153,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532066552.586, "dur": 18.286, + "args": { + "External id": 1410154,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532066585.347, "dur": 19.845, + "args": { + "External id": 1410155,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066695.514, "dur": 21.806, + "args": { + "External id": 1410156,"Record function id": 0, "Ev Idx": 2667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066699.570, "dur": 16.653, + "args": { + "External id": 1410157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066707.690, "dur": 7.425, + "args": { + "External id": 1410158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066709.875, "dur": 5.105, + "args": { + "External id": 1410159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066721.786, "dur": 6.703, + "args": { + "External id": 1410160,"Record function id": 0, "Ev Idx": 2671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066723.650, "dur": 4.273, + "args": { + "External id": 1410161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066724.939, "dur": 2.463, + "args": { + "External id": 1410162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066726.010, "dur": 1.280, + "args": { + "External id": 1410163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066732.346, "dur": 8.297, + "args": { + "External id": 1410164,"Record function id": 0, "Ev Idx": 2675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066734.332, "dur": 5.764, + "args": { + "External id": 1410165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066735.050, "dur": 4.538, + "args": { + "External id": 1410166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066735.767, "dur": 3.739, + "args": { + "External id": 1410167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066744.559, "dur": 5.843, + "args": { + "External id": 1410168,"Record function id": 0, "Ev Idx": 2679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066746.493, "dur": 3.422, + "args": { + "External id": 1410169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066747.382, "dur": 2.015, + "args": { + "External id": 1410170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066748.245, "dur": 1.046, + "args": { + "External id": 1410171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066754.276, "dur": 4.773, + "args": { + "External id": 1410172,"Record function id": 0, "Ev Idx": 2683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066755.944, "dur": 2.633, + "args": { + "External id": 1410173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066756.939, "dur": 1.158, + "args": { + "External id": 1410174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066757.317, "dur": 0.690, + "args": { + "External id": 1410175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066762.962, "dur": 5.758, + "args": { + "External id": 1410176,"Record function id": 0, "Ev Idx": 2687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066764.859, "dur": 3.351, + "args": { + "External id": 1410177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066766.061, "dur": 1.655, + "args": { + "External id": 1410178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066766.905, "dur": 0.683, + "args": { + "External id": 1410179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066772.698, "dur": 5.411, + "args": { + "External id": 1410180,"Record function id": 0, "Ev Idx": 2691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066774.085, "dur": 3.551, + "args": { + "External id": 1410181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066775.186, "dur": 1.850, + "args": { + "External id": 1410182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066775.752, "dur": 1.151, + "args": { + "External id": 1410183,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066781.822, "dur": 4.810, + "args": { + "External id": 1410184,"Record function id": 0, "Ev Idx": 2695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066783.393, "dur": 2.755, + "args": { + "External id": 1410185,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066784.381, "dur": 1.288, + "args": { + "External id": 1410186,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066784.720, "dur": 0.817, + "args": { + "External id": 1410187,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066790.235, "dur": 5.705, + "args": { + "External id": 1410188,"Record function id": 0, "Ev Idx": 2699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532066791.708, "dur": 3.724, + "args": { + "External id": 1410189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066792.495, "dur": 2.435, + "args": { + "External id": 1410190,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532066794.048, "dur": 0.736, + "args": { + "External id": 1410191,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532066800.535, "dur": 61749.729, + "args": { + "External id": 1410192,"Record function id": 0, "Sequence number": 15108881, "Fwd thread id": 1, "Ev Idx": 2703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532066801.990, "dur": 61737.840, + "args": { + "External id": 1410193,"Sequence number": 15108881, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2704 + } + }, + { + "ph": "f", "id": 185, "pid": 2338710, "tid": 2379450, "ts": 6410532066801.990, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410532066836.516, "dur": 45.519, + "args": { + "External id": 1410194,"Record function id": 0, "Ev Idx": 2705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410532066891.380, "dur": 73.883, + "args": { + "External id": 1410195,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410532066971.913, "dur": 61558.270, + "args": { + "External id": 1410196,"Record function id": 0, "Ev Idx": 2707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532067119.725, "dur": 9.578, + "args": { + "External id": 1410197,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532067143.117, "dur": 7.923, + "args": { + "External id": 1410198,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532067169.938, "dur": 60305.593, + "args": { + "External id": 1410199,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532067186.758, "dur": 60272.819, + "args": { + "External id": 1410200,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532067318.695, "dur": 22.463, + "args": { + "External id": 1410201,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532067364.842, "dur": 60019.364, + "args": { + "External id": 1410202,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532067368.331, "dur": 60014.408, + "args": { + "External id": 1410203,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532067377.285, "dur": 11.485, + "args": { + "External id": 1410204,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532067391.245, "dur": 59984.936, + "args": { + "External id": 1410205,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532127606.985, "dur": 16.556, + "args": { + "External id": 1410206,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532127611.934, "dur": 11.127, + "args": { + "External id": 1410207,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532127659.502, "dur": 472.194, + "args": { + "External id": 1410208,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532127692.858, "dur": 431.987, + "args": { + "External id": 1410209,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2720, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532127707.327, "dur": 410.258, + "args": { + "External id": 1410210,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532128156.976, "dur": 3.104, + "args": { + "External id": 1410211,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2722, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128236.026, "dur": 8.026, + "args": { + "External id": 1410212,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128298.738, "dur": 1.529, + "args": { + "External id": 1410213,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128319.769, "dur": 3.874, + "args": { + "External id": 1410214,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128339.333, "dur": 1.408, + "args": { + "External id": 1410215,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128354.950, "dur": 1.406, + "args": { + "External id": 1410216,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128370.547, "dur": 1.744, + "args": { + "External id": 1410217,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128385.409, "dur": 3.934, + "args": { + "External id": 1410218,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128402.479, "dur": 3.467, + "args": { + "External id": 1410219,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128446.920, "dur": 2.381, + "args": { + "External id": 1410220,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532128568.866, "dur": 3561.981, + "args": { + "External id": 1410221,"Record function id": 0, "Ev Idx": 2732 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410532128592.444, "dur": 1321.672, + "args": { + "External id": 1410222,"Record function id": 0, "Ev Idx": 2733 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410532128611.931, "dur": 389.339, + "args": { + "External id": 1410223,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128722.252, "dur": 5.149, + "args": { + "External id": 1410224,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128731.124, "dur": 1.504, + "args": { + "External id": 1410225,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128734.908, "dur": 3.753, + "args": { + "External id": 1410226,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128740.594, "dur": 1.274, + "args": { + "External id": 1410227,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128743.517, "dur": 1.407, + "args": { + "External id": 1410228,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128747.063, "dur": 0.981, + "args": { + "External id": 1410229,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128750.236, "dur": 3.051, + "args": { + "External id": 1410230,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128755.014, "dur": 1.250, + "args": { + "External id": 1410231,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128758.056, "dur": 1.150, + "args": { + "External id": 1410232,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532128761.457, "dur": 1.097, + "args": { + "External id": 1410233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532128783.416, "dur": 179.867, + "args": { + "External id": 1410234,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532128803.288, "dur": 154.685, + "args": { + "External id": 1410235,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532128820.891, "dur": 18.042, + "args": { + "External id": 1410236,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532128843.464, "dur": 78.618, + "args": { + "External id": 1410237,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532128846.523, "dur": 75.129, + "args": { + "External id": 1410238,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532128852.011, "dur": 6.473, + "args": { + "External id": 1410239,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532128860.666, "dur": 60.305, + "args": { + "External id": 1410240,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2751 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.17", "pid": 2338710, "tid": 2379450, + "ts": 6410532129167.565, "dur": 734.337, + "args": { + "External id": 1410241,"Record function id": 0, "Ev Idx": 2752 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410532129188.702, "dur": 697.719, + "args": { + "External id": 1410242,"Record function id": 0, "Ev Idx": 2753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532129264.828, "dur": 7.665, + "args": { + "External id": 1410243,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532129290.274, "dur": 40.830, + "args": { + "External id": 1410244,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129296.705, "dur": 2.167, + "args": { + "External id": 1410245,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129301.603, "dur": 0.556, + "args": { + "External id": 1410246,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129304.349, "dur": 0.730, + "args": { + "External id": 1410247,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129307.199, "dur": 0.640, + "args": { + "External id": 1410248,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129309.925, "dur": 0.567, + "args": { + "External id": 1410249,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129312.825, "dur": 3.026, + "args": { + "External id": 1410250,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129318.116, "dur": 0.478, + "args": { + "External id": 1410251,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129320.844, "dur": 0.821, + "args": { + "External id": 1410252,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129323.879, "dur": 0.471, + "args": { + "External id": 1410253,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532129349.363, "dur": 60.825, + "args": { + "External id": 1410254,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532129469.392, "dur": 147.560, + "args": { + "External id": 1410255,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532129483.740, "dur": 6.430, + "args": { + "External id": 1410256,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532129496.751, "dur": 13.438, + "args": { + "External id": 1410257,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532129501.996, "dur": 7.720, + "args": { + "External id": 1410258,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129507.050, "dur": 0.681, + "args": { + "External id": 1410259,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532129518.741, "dur": 32.205, + "args": { + "External id": 1410260,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129522.093, "dur": 0.699, + "args": { + "External id": 1410261,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129525.310, "dur": 0.478, + "args": { + "External id": 1410262,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129528.087, "dur": 2.820, + "args": { + "External id": 1410263,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129533.139, "dur": 0.447, + "args": { + "External id": 1410264,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129535.732, "dur": 0.365, + "args": { + "External id": 1410265,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129537.940, "dur": 0.450, + "args": { + "External id": 1410266,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129540.628, "dur": 0.379, + "args": { + "External id": 1410267,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129543.381, "dur": 0.523, + "args": { + "External id": 1410268,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532129545.666, "dur": 0.466, + "args": { + "External id": 1410269,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532129566.642, "dur": 40.822, + "args": { + "External id": 1410270,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532129673.246, "dur": 131.603, + "args": { + "External id": 1410271,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532129698.846, "dur": 101.740, + "args": { + "External id": 1410272,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2783, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532129710.252, "dur": 85.334, + "args": { + "External id": 1410273,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532129820.002, "dur": 2.061, + "args": { + "External id": 1410274,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2785, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532129923.280, "dur": 2178.875, + "args": { + "External id": 1410275,"Sequence number": 15108880, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2786 + } + }, + { + "ph": "f", "id": 186, "pid": 2338710, "tid": 2379450, "ts": 6410532129923.280, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532130048.527, "dur": 169.762, + "args": { + "External id": 1410276,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532130273.318, "dur": 49.828, + "args": { + "External id": 1410277,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532130346.802, "dur": 61.801, + "args": { + "External id": 1410278,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532130441.266, "dur": 46.306, + "args": { + "External id": 1410279,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532130497.916, "dur": 39.113, + "args": { + "External id": 1410280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532130545.975, "dur": 34.369, + "args": { + "External id": 1410281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532130589.836, "dur": 35.339, + "args": { + "External id": 1410282,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532130656.247, "dur": 29.406, + "args": { + "External id": 1410283,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532130708.017, "dur": 33.262, + "args": { + "External id": 1410284,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532130766.935, "dur": 23.160, + "args": { + "External id": 1410285,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532130805.088, "dur": 18.164, + "args": { + "External id": 1410286,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532130834.054, "dur": 46.124, + "args": { + "External id": 1410287,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532130884.355, "dur": 39.449, + "args": { + "External id": 1410288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532130960.645, "dur": 383.544, + "args": { + "External id": 1410289,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532131053.157, "dur": 46.821, + "args": { + "External id": 1410290,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532131119.163, "dur": 7.486, + "args": { + "External id": 1410291,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532131128.702, "dur": 2.653, + "args": { + "External id": 1410292,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532131132.635, "dur": 2.253, + "args": { + "External id": 1410293,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532131197.173, "dur": 5.845, + "args": { + "External id": 1410294,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532131199.287, "dur": 3.555, + "args": { + "External id": 1410295,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532131205.788, "dur": 42.340, + "args": { + "External id": 1410296,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532131212.595, "dur": 4.714, + "args": { + "External id": 1410297,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532131250.687, "dur": 2.391, + "args": { + "External id": 1410298,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532131252.254, "dur": 0.714, + "args": { + "External id": 1410299,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532131254.848, "dur": 22.942, + "args": { + "External id": 1410300,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532131257.569, "dur": 0.923, + "args": { + "External id": 1410301,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532131392.087, "dur": 56.198, + "args": { + "External id": 1410302,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532131473.008, "dur": 21.715, + "args": { + "External id": 1410303,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532131506.975, "dur": 66.048, + "args": { + "External id": 1410304,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532131581.868, "dur": 54.364, + "args": { + "External id": 1410305,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532131649.642, "dur": 27.986, + "args": { + "External id": 1410306,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532131685.631, "dur": 37.803, + "args": { + "External id": 1410307,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532131733.022, "dur": 35.207, + "args": { + "External id": 1410308,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532131777.147, "dur": 36.226, + "args": { + "External id": 1410309,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532131837.938, "dur": 29.976, + "args": { + "External id": 1410310,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532131889.436, "dur": 30.264, + "args": { + "External id": 1410311,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532131936.070, "dur": 22.305, + "args": { + "External id": 1410312,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532131977.107, "dur": 19.348, + "args": { + "External id": 1410313,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532132010.960, "dur": 19.180, + "args": { + "External id": 1410314,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132157.351, "dur": 19.158, + "args": { + "External id": 1410315,"Record function id": 0, "Ev Idx": 2826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132161.752, "dur": 13.597, + "args": { + "External id": 1410316,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132167.042, "dur": 7.265, + "args": { + "External id": 1410317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132169.171, "dur": 4.986, + "args": { + "External id": 1410318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132181.128, "dur": 7.188, + "args": { + "External id": 1410319,"Record function id": 0, "Ev Idx": 2830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132183.127, "dur": 4.633, + "args": { + "External id": 1410320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132184.445, "dur": 2.809, + "args": { + "External id": 1410321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132185.546, "dur": 1.610, + "args": { + "External id": 1410322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132192.424, "dur": 8.858, + "args": { + "External id": 1410323,"Record function id": 0, "Ev Idx": 2834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132194.415, "dur": 6.377, + "args": { + "External id": 1410324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132195.323, "dur": 4.954, + "args": { + "External id": 1410325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132196.135, "dur": 4.037, + "args": { + "External id": 1410326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132205.382, "dur": 6.075, + "args": { + "External id": 1410327,"Record function id": 0, "Ev Idx": 2838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132207.227, "dur": 3.736, + "args": { + "External id": 1410328,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132208.361, "dur": 2.138, + "args": { + "External id": 1410329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132209.332, "dur": 1.095, + "args": { + "External id": 1410330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132215.383, "dur": 5.152, + "args": { + "External id": 1410331,"Record function id": 0, "Ev Idx": 2842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132216.659, "dur": 3.343, + "args": { + "External id": 1410332,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132217.758, "dur": 1.785, + "args": { + "External id": 1410333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132218.598, "dur": 0.824, + "args": { + "External id": 1410334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132224.552, "dur": 5.234, + "args": { + "External id": 1410335,"Record function id": 0, "Ev Idx": 2846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132226.260, "dur": 3.039, + "args": { + "External id": 1410336,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132226.942, "dur": 1.823, + "args": { + "External id": 1410337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132227.798, "dur": 0.841, + "args": { + "External id": 1410338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132234.022, "dur": 4.270, + "args": { + "External id": 1410339,"Record function id": 0, "Ev Idx": 2850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132235.360, "dur": 2.422, + "args": { + "External id": 1410340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132236.052, "dur": 1.239, + "args": { + "External id": 1410341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132236.396, "dur": 0.772, + "args": { + "External id": 1410342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132242.152, "dur": 4.440, + "args": { + "External id": 1410343,"Record function id": 0, "Ev Idx": 2854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132243.640, "dur": 2.478, + "args": { + "External id": 1410344,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132244.317, "dur": 1.306, + "args": { + "External id": 1410345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132244.658, "dur": 0.844, + "args": { + "External id": 1410346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132250.427, "dur": 4.654, + "args": { + "External id": 1410347,"Record function id": 0, "Ev Idx": 2858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532132251.797, "dur": 2.799, + "args": { + "External id": 1410348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132252.691, "dur": 1.446, + "args": { + "External id": 1410349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532132253.384, "dur": 0.640, + "args": { + "External id": 1410350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532132259.948, "dur": 63188.270, + "args": { + "External id": 1410351,"Record function id": 0, "Sequence number": 15108879, "Fwd thread id": 1, "Ev Idx": 2862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532132261.571, "dur": 63174.264, + "args": { + "External id": 1410352,"Sequence number": 15108879, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2863 + } + }, + { + "ph": "f", "id": 187, "pid": 2338710, "tid": 2379450, "ts": 6410532132261.571, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410532132298.007, "dur": 46.728, + "args": { + "External id": 1410353,"Record function id": 0, "Ev Idx": 2864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410532132355.476, "dur": 94.722, + "args": { + "External id": 1410354,"Record function id": 0, "Ev Idx": 2865 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410532132459.355, "dur": 62950.360, + "args": { + "External id": 1410355,"Record function id": 0, "Ev Idx": 2866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532132569.793, "dur": 8.859, + "args": { + "External id": 1410356,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532132590.626, "dur": 8.151, + "args": { + "External id": 1410357,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532132616.195, "dur": 61691.229, + "args": { + "External id": 1410358,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532132632.683, "dur": 61658.765, + "args": { + "External id": 1410359,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532132769.511, "dur": 20.807, + "args": { + "External id": 1410360,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532132814.139, "dur": 61413.506, + "args": { + "External id": 1410361,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532132817.799, "dur": 61408.305, + "args": { + "External id": 1410362,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532132823.516, "dur": 10.760, + "args": { + "External id": 1410363,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532132836.928, "dur": 61382.179, + "args": { + "External id": 1410364,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532194452.627, "dur": 17.481, + "args": { + "External id": 1410365,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532194458.099, "dur": 11.221, + "args": { + "External id": 1410366,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532194511.079, "dur": 470.179, + "args": { + "External id": 1410367,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532194544.974, "dur": 429.955, + "args": { + "External id": 1410368,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2879, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532194559.236, "dur": 408.026, + "args": { + "External id": 1410369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532195004.870, "dur": 2.417, + "args": { + "External id": 1410370,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2881, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195141.454, "dur": 8.351, + "args": { + "External id": 1410371,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195206.358, "dur": 1.834, + "args": { + "External id": 1410372,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195230.583, "dur": 3.481, + "args": { + "External id": 1410373,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195249.390, "dur": 0.866, + "args": { + "External id": 1410374,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195264.634, "dur": 1.243, + "args": { + "External id": 1410375,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195279.587, "dur": 1.474, + "args": { + "External id": 1410376,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195297.560, "dur": 3.375, + "args": { + "External id": 1410377,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195314.981, "dur": 3.000, + "args": { + "External id": 1410378,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195332.013, "dur": 1.151, + "args": { + "External id": 1410379,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532195467.862, "dur": 4258.198, + "args": { + "External id": 1410380,"Record function id": 0, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410532195493.792, "dur": 1343.871, + "args": { + "External id": 1410381,"Record function id": 0, "Ev Idx": 2892 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410532195514.414, "dur": 414.979, + "args": { + "External id": 1410382,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195628.846, "dur": 5.665, + "args": { + "External id": 1410383,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195638.798, "dur": 1.257, + "args": { + "External id": 1410384,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195642.313, "dur": 3.487, + "args": { + "External id": 1410385,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195648.267, "dur": 1.329, + "args": { + "External id": 1410386,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195651.475, "dur": 1.087, + "args": { + "External id": 1410387,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195654.891, "dur": 1.160, + "args": { + "External id": 1410388,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195658.058, "dur": 2.640, + "args": { + "External id": 1410389,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195663.028, "dur": 1.393, + "args": { + "External id": 1410390,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195666.282, "dur": 1.205, + "args": { + "External id": 1410391,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532195669.258, "dur": 1.135, + "args": { + "External id": 1410392,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532195705.416, "dur": 185.114, + "args": { + "External id": 1410393,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532195725.227, "dur": 159.336, + "args": { + "External id": 1410394,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532195744.605, "dur": 19.093, + "args": { + "External id": 1410395,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532195768.657, "dur": 80.220, + "args": { + "External id": 1410396,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532195772.080, "dur": 76.418, + "args": { + "External id": 1410397,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532195777.253, "dur": 6.740, + "args": { + "External id": 1410398,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532195786.270, "dur": 61.448, + "args": { + "External id": 1410399,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2910 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.16", "pid": 2338710, "tid": 2379450, + "ts": 6410532196033.422, "dur": 793.404, + "args": { + "External id": 1410400,"Record function id": 0, "Ev Idx": 2911 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410532196052.944, "dur": 758.418, + "args": { + "External id": 1410401,"Record function id": 0, "Ev Idx": 2912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532196204.271, "dur": 9.163, + "args": { + "External id": 1410402,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532196231.478, "dur": 39.840, + "args": { + "External id": 1410403,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196238.313, "dur": 2.071, + "args": { + "External id": 1410404,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196243.458, "dur": 0.503, + "args": { + "External id": 1410405,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196246.377, "dur": 0.466, + "args": { + "External id": 1410406,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196248.664, "dur": 0.637, + "args": { + "External id": 1410407,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196251.583, "dur": 0.476, + "args": { + "External id": 1410408,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196254.096, "dur": 2.928, + "args": { + "External id": 1410409,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196259.088, "dur": 0.545, + "args": { + "External id": 1410410,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196261.847, "dur": 0.477, + "args": { + "External id": 1410411,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196264.109, "dur": 0.369, + "args": { + "External id": 1410412,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532196284.414, "dur": 57.920, + "args": { + "External id": 1410413,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532196382.024, "dur": 158.520, + "args": { + "External id": 1410414,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532196394.523, "dur": 4.433, + "args": { + "External id": 1410415,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532196405.384, "dur": 31.874, + "args": { + "External id": 1410416,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532196410.697, "dur": 26.066, + "args": { + "External id": 1410417,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196432.464, "dur": 1.680, + "args": { + "External id": 1410418,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532196447.478, "dur": 31.991, + "args": { + "External id": 1410419,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196450.849, "dur": 0.634, + "args": { + "External id": 1410420,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196453.669, "dur": 0.407, + "args": { + "External id": 1410421,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196456.292, "dur": 2.622, + "args": { + "External id": 1410422,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196461.167, "dur": 0.502, + "args": { + "External id": 1410423,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196463.483, "dur": 0.468, + "args": { + "External id": 1410424,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196466.087, "dur": 0.419, + "args": { + "External id": 1410425,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196468.510, "dur": 0.681, + "args": { + "External id": 1410426,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196471.010, "dur": 0.409, + "args": { + "External id": 1410427,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532196473.504, "dur": 0.600, + "args": { + "External id": 1410428,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532196494.128, "dur": 37.195, + "args": { + "External id": 1410429,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532196597.591, "dur": 133.573, + "args": { + "External id": 1410430,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532196624.829, "dur": 102.062, + "args": { + "External id": 1410431,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2942, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532196636.647, "dur": 85.462, + "args": { + "External id": 1410432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532196747.292, "dur": 2.383, + "args": { + "External id": 1410433,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2944, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532196847.693, "dur": 2845.104, + "args": { + "External id": 1410434,"Sequence number": 15108878, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2945 + } + }, + { + "ph": "f", "id": 188, "pid": 2338710, "tid": 2379450, "ts": 6410532196847.693, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532196978.736, "dur": 178.282, + "args": { + "External id": 1410435,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532197207.853, "dur": 51.104, + "args": { + "External id": 1410436,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532197282.903, "dur": 67.491, + "args": { + "External id": 1410437,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532197365.092, "dur": 40.894, + "args": { + "External id": 1410438,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532197431.650, "dur": 46.732, + "args": { + "External id": 1410439,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532197491.520, "dur": 33.970, + "args": { + "External id": 1410440,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532197535.600, "dur": 34.155, + "args": { + "External id": 1410441,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532197600.857, "dur": 29.022, + "args": { + "External id": 1410442,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532197674.339, "dur": 33.301, + "args": { + "External id": 1410443,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532197737.572, "dur": 22.647, + "args": { + "External id": 1410444,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532197776.718, "dur": 17.837, + "args": { + "External id": 1410445,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532197806.178, "dur": 45.631, + "args": { + "External id": 1410446,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532197856.039, "dur": 59.350, + "args": { + "External id": 1410447,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532197960.570, "dur": 356.372, + "args": { + "External id": 1410448,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532198098.946, "dur": 8.861, + "args": { + "External id": 1410449,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532198111.041, "dur": 3.661, + "args": { + "External id": 1410450,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532198124.668, "dur": 2.487, + "args": { + "External id": 1410451,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532198128.983, "dur": 2.689, + "args": { + "External id": 1410452,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532198189.175, "dur": 6.151, + "args": { + "External id": 1410453,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532198191.812, "dur": 3.238, + "args": { + "External id": 1410454,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532198198.102, "dur": 39.714, + "args": { + "External id": 1410455,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532198204.653, "dur": 4.579, + "args": { + "External id": 1410456,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532198240.024, "dur": 2.896, + "args": { + "External id": 1410457,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532198241.938, "dur": 0.828, + "args": { + "External id": 1410458,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532198244.473, "dur": 17.131, + "args": { + "External id": 1410459,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532198247.042, "dur": 0.813, + "args": { + "External id": 1410460,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532198362.874, "dur": 33.627, + "args": { + "External id": 1410461,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532198434.265, "dur": 22.736, + "args": { + "External id": 1410462,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532198470.600, "dur": 63.466, + "args": { + "External id": 1410463,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532198543.532, "dur": 49.600, + "args": { + "External id": 1410464,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532198606.474, "dur": 27.453, + "args": { + "External id": 1410465,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532198641.579, "dur": 44.675, + "args": { + "External id": 1410466,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532198699.706, "dur": 51.558, + "args": { + "External id": 1410467,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532198766.913, "dur": 55.585, + "args": { + "External id": 1410468,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532198857.332, "dur": 45.445, + "args": { + "External id": 1410469,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532198934.502, "dur": 45.993, + "args": { + "External id": 1410470,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532199009.001, "dur": 31.119, + "args": { + "External id": 1410471,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532199115.205, "dur": 231.115, + "args": { + "External id": 1410472,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532199587.643, "dur": 45.725, + "args": { + "External id": 1410473,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199754.335, "dur": 20.232, + "args": { + "External id": 1410474,"Record function id": 0, "Ev Idx": 2985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199758.916, "dur": 14.357, + "args": { + "External id": 1410475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199764.430, "dur": 7.824, + "args": { + "External id": 1410476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199766.898, "dur": 5.212, + "args": { + "External id": 1410477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199779.586, "dur": 6.230, + "args": { + "External id": 1410478,"Record function id": 0, "Ev Idx": 2989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199781.383, "dur": 3.949, + "args": { + "External id": 1410479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199782.186, "dur": 2.557, + "args": { + "External id": 1410480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199783.310, "dur": 1.296, + "args": { + "External id": 1410481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199790.037, "dur": 8.042, + "args": { + "External id": 1410482,"Record function id": 0, "Ev Idx": 2993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199791.750, "dur": 5.873, + "args": { + "External id": 1410483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199792.247, "dur": 4.878, + "args": { + "External id": 1410484,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199793.030, "dur": 3.978, + "args": { + "External id": 1410485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199801.953, "dur": 4.656, + "args": { + "External id": 1410486,"Record function id": 0, "Ev Idx": 2997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199803.436, "dur": 2.698, + "args": { + "External id": 1410487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199804.070, "dur": 1.580, + "args": { + "External id": 1410488,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199804.730, "dur": 0.834, + "args": { + "External id": 1410489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199810.476, "dur": 4.688, + "args": { + "External id": 1410490,"Record function id": 0, "Ev Idx": 3001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199811.638, "dur": 3.052, + "args": { + "External id": 1410491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199812.310, "dur": 1.853, + "args": { + "External id": 1410492,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199813.052, "dur": 0.994, + "args": { + "External id": 1410493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199819.290, "dur": 4.815, + "args": { + "External id": 1410494,"Record function id": 0, "Ev Idx": 3005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199820.872, "dur": 2.774, + "args": { + "External id": 1410495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199821.582, "dur": 1.449, + "args": { + "External id": 1410496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199822.238, "dur": 0.665, + "args": { + "External id": 1410497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199828.183, "dur": 4.442, + "args": { + "External id": 1410498,"Record function id": 0, "Ev Idx": 3009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199829.673, "dur": 2.479, + "args": { + "External id": 1410499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199830.501, "dur": 1.162, + "args": { + "External id": 1410500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199830.851, "dur": 0.656, + "args": { + "External id": 1410501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199836.470, "dur": 4.501, + "args": { + "External id": 1410502,"Record function id": 0, "Ev Idx": 3013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199837.983, "dur": 2.531, + "args": { + "External id": 1410503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199838.818, "dur": 1.186, + "args": { + "External id": 1410504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199839.213, "dur": 0.693, + "args": { + "External id": 1410505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199845.071, "dur": 4.439, + "args": { + "External id": 1410506,"Record function id": 0, "Ev Idx": 3017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532199846.410, "dur": 2.649, + "args": { + "External id": 1410507,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199847.046, "dur": 1.504, + "args": { + "External id": 1410508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532199847.579, "dur": 0.857, + "args": { + "External id": 1410509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532199854.367, "dur": 60337.331, + "args": { + "External id": 1410510,"Record function id": 0, "Sequence number": 15108877, "Fwd thread id": 1, "Ev Idx": 3021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532199856.014, "dur": 60324.486, + "args": { + "External id": 1410511,"Sequence number": 15108877, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3022 + } + }, + { + "ph": "f", "id": 189, "pid": 2338710, "tid": 2379450, "ts": 6410532199856.014, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410532199893.567, "dur": 47.294, + "args": { + "External id": 1410512,"Record function id": 0, "Ev Idx": 3023 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410532199950.542, "dur": 76.314, + "args": { + "External id": 1410513,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410532200033.845, "dur": 60136.375, + "args": { + "External id": 1410514,"Record function id": 0, "Ev Idx": 3025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532200195.857, "dur": 10.224, + "args": { + "External id": 1410515,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532200218.484, "dur": 8.209, + "args": { + "External id": 1410516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532200244.242, "dur": 58894.142, + "args": { + "External id": 1410517,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532200261.084, "dur": 58862.737, + "args": { + "External id": 1410518,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532200374.451, "dur": 22.118, + "args": { + "External id": 1410519,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532200440.594, "dur": 58596.305, + "args": { + "External id": 1410520,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532200444.230, "dur": 58591.653, + "args": { + "External id": 1410521,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532200451.033, "dur": 12.778, + "args": { + "External id": 1410522,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532200466.314, "dur": 58564.027, + "args": { + "External id": 1410523,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532259264.851, "dur": 16.567, + "args": { + "External id": 1410524,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532259270.105, "dur": 10.941, + "args": { + "External id": 1410525,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532259318.178, "dur": 429.910, + "args": { + "External id": 1410526,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532259351.285, "dur": 390.307, + "args": { + "External id": 1410527,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3038, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532259365.649, "dur": 369.882, + "args": { + "External id": 1410528,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532259771.692, "dur": 2.675, + "args": { + "External id": 1410529,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3040, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532259847.047, "dur": 7.970, + "args": { + "External id": 1410530,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532259911.973, "dur": 1.538, + "args": { + "External id": 1410531,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532259934.337, "dur": 3.580, + "args": { + "External id": 1410532,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532259953.297, "dur": 1.074, + "args": { + "External id": 1410533,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532259968.049, "dur": 1.049, + "args": { + "External id": 1410534,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532259983.460, "dur": 1.268, + "args": { + "External id": 1410535,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532259998.867, "dur": 3.357, + "args": { + "External id": 1410536,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260015.933, "dur": 3.421, + "args": { + "External id": 1410537,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260035.674, "dur": 1.351, + "args": { + "External id": 1410538,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532260211.540, "dur": 3598.915, + "args": { + "External id": 1410539,"Record function id": 0, "Ev Idx": 3050 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410532260234.378, "dur": 1401.743, + "args": { + "External id": 1410540,"Record function id": 0, "Ev Idx": 3051 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410532260252.304, "dur": 446.620, + "args": { + "External id": 1410541,"Record function id": 0, "Ev Idx": 3052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260368.577, "dur": 5.958, + "args": { + "External id": 1410542,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260378.865, "dur": 1.323, + "args": { + "External id": 1410543,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260382.695, "dur": 3.901, + "args": { + "External id": 1410544,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260388.808, "dur": 1.027, + "args": { + "External id": 1410545,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260391.902, "dur": 1.370, + "args": { + "External id": 1410546,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260395.305, "dur": 1.376, + "args": { + "External id": 1410547,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260398.737, "dur": 2.780, + "args": { + "External id": 1410548,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260403.416, "dur": 1.132, + "args": { + "External id": 1410549,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260406.797, "dur": 1.037, + "args": { + "External id": 1410550,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532260409.555, "dur": 1.065, + "args": { + "External id": 1410551,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532260467.320, "dur": 191.650, + "args": { + "External id": 1410552,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532260488.907, "dur": 163.848, + "args": { + "External id": 1410553,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532260507.958, "dur": 21.406, + "args": { + "External id": 1410554,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532260534.314, "dur": 80.728, + "args": { + "External id": 1410555,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532260537.349, "dur": 77.168, + "args": { + "External id": 1410556,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260542.630, "dur": 7.523, + "args": { + "External id": 1410557,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532260552.612, "dur": 61.143, + "args": { + "External id": 1410558,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.15", "pid": 2338710, "tid": 2379450, + "ts": 6410532260808.609, "dur": 817.695, + "args": { + "External id": 1410559,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410532260829.911, "dur": 779.559, + "args": { + "External id": 1410560,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532260928.686, "dur": 16.717, + "args": { + "External id": 1410561,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532260963.926, "dur": 38.402, + "args": { + "External id": 1410562,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260970.021, "dur": 2.170, + "args": { + "External id": 1410563,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260974.973, "dur": 0.432, + "args": { + "External id": 1410564,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260977.273, "dur": 0.532, + "args": { + "External id": 1410565,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260980.134, "dur": 0.701, + "args": { + "External id": 1410566,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260982.821, "dur": 0.496, + "args": { + "External id": 1410567,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260985.017, "dur": 2.595, + "args": { + "External id": 1410568,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260989.795, "dur": 0.639, + "args": { + "External id": 1410569,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260992.329, "dur": 0.417, + "args": { + "External id": 1410570,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532260994.514, "dur": 0.489, + "args": { + "External id": 1410571,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532261015.081, "dur": 99.093, + "args": { + "External id": 1410572,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532261162.608, "dur": 143.014, + "args": { + "External id": 1410573,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532261176.600, "dur": 5.725, + "args": { + "External id": 1410574,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532261188.836, "dur": 13.249, + "args": { + "External id": 1410575,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532261193.782, "dur": 7.779, + "args": { + "External id": 1410576,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261198.703, "dur": 0.885, + "args": { + "External id": 1410577,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532261210.609, "dur": 33.227, + "args": { + "External id": 1410578,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261213.951, "dur": 0.499, + "args": { + "External id": 1410579,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261217.339, "dur": 0.531, + "args": { + "External id": 1410580,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261219.555, "dur": 2.913, + "args": { + "External id": 1410581,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261225.314, "dur": 0.643, + "args": { + "External id": 1410582,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261227.940, "dur": 0.368, + "args": { + "External id": 1410583,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261230.357, "dur": 0.747, + "args": { + "External id": 1410584,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261233.114, "dur": 0.408, + "args": { + "External id": 1410585,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261235.460, "dur": 0.430, + "args": { + "External id": 1410586,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532261237.790, "dur": 0.489, + "args": { + "External id": 1410587,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532261258.811, "dur": 37.726, + "args": { + "External id": 1410588,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532261365.150, "dur": 159.145, + "args": { + "External id": 1410589,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532261392.647, "dur": 126.630, + "args": { + "External id": 1410590,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3101, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532261404.622, "dur": 109.553, + "args": { + "External id": 1410591,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532261542.580, "dur": 2.588, + "args": { + "External id": 1410592,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3103, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532261644.675, "dur": 2137.919, + "args": { + "External id": 1410593,"Sequence number": 15108876, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3104 + } + }, + { + "ph": "f", "id": 190, "pid": 2338710, "tid": 2379450, "ts": 6410532261644.675, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532261779.763, "dur": 122.245, + "args": { + "External id": 1410594,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532261964.641, "dur": 47.764, + "args": { + "External id": 1410595,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532262035.093, "dur": 111.985, + "args": { + "External id": 1410596,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532262167.554, "dur": 44.566, + "args": { + "External id": 1410597,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532262221.605, "dur": 39.953, + "args": { + "External id": 1410598,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532262270.477, "dur": 32.875, + "args": { + "External id": 1410599,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532262312.276, "dur": 33.736, + "args": { + "External id": 1410600,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532262378.936, "dur": 28.517, + "args": { + "External id": 1410601,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532262445.046, "dur": 34.473, + "args": { + "External id": 1410602,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532262505.206, "dur": 23.196, + "args": { + "External id": 1410603,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532262543.646, "dur": 16.530, + "args": { + "External id": 1410604,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532262571.255, "dur": 50.910, + "args": { + "External id": 1410605,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532262626.892, "dur": 39.844, + "args": { + "External id": 1410606,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532262704.556, "dur": 334.751, + "args": { + "External id": 1410607,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532262826.314, "dur": 8.866, + "args": { + "External id": 1410608,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532262838.199, "dur": 3.145, + "args": { + "External id": 1410609,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532262842.950, "dur": 2.796, + "args": { + "External id": 1410610,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532262847.525, "dur": 2.230, + "args": { + "External id": 1410611,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532262909.496, "dur": 5.722, + "args": { + "External id": 1410612,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532262911.866, "dur": 3.135, + "args": { + "External id": 1410613,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532262918.281, "dur": 43.885, + "args": { + "External id": 1410614,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532262928.042, "dur": 4.411, + "args": { + "External id": 1410615,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532262964.384, "dur": 2.415, + "args": { + "External id": 1410616,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532262965.820, "dur": 0.820, + "args": { + "External id": 1410617,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532262968.917, "dur": 19.316, + "args": { + "External id": 1410618,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532262971.557, "dur": 0.686, + "args": { + "External id": 1410619,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532263125.878, "dur": 45.815, + "args": { + "External id": 1410620,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532263192.087, "dur": 20.387, + "args": { + "External id": 1410621,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532263222.887, "dur": 60.314, + "args": { + "External id": 1410622,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532263292.542, "dur": 49.071, + "args": { + "External id": 1410623,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532263355.518, "dur": 27.177, + "args": { + "External id": 1410624,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532263390.616, "dur": 54.287, + "args": { + "External id": 1410625,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532263458.507, "dur": 37.201, + "args": { + "External id": 1410626,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532263504.743, "dur": 35.280, + "args": { + "External id": 1410627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532263564.694, "dur": 29.159, + "args": { + "External id": 1410628,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532263612.527, "dur": 28.076, + "args": { + "External id": 1410629,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532263657.838, "dur": 20.430, + "args": { + "External id": 1410630,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532263696.735, "dur": 17.214, + "args": { + "External id": 1410631,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532263728.772, "dur": 17.874, + "args": { + "External id": 1410632,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263835.704, "dur": 18.041, + "args": { + "External id": 1410633,"Record function id": 0, "Ev Idx": 3144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263839.786, "dur": 12.915, + "args": { + "External id": 1410634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263844.501, "dur": 7.074, + "args": { + "External id": 1410635,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263846.623, "dur": 4.796, + "args": { + "External id": 1410636,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263858.414, "dur": 32.927, + "args": { + "External id": 1410637,"Record function id": 0, "Ev Idx": 3148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263860.120, "dur": 30.475, + "args": { + "External id": 1410638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263861.168, "dur": 28.727, + "args": { + "External id": 1410639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263888.450, "dur": 1.307, + "args": { + "External id": 1410640,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263895.529, "dur": 7.932, + "args": { + "External id": 1410641,"Record function id": 0, "Ev Idx": 3152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263897.350, "dur": 5.596, + "args": { + "External id": 1410642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263898.237, "dur": 4.151, + "args": { + "External id": 1410643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263899.083, "dur": 3.172, + "args": { + "External id": 1410644,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263907.821, "dur": 4.354, + "args": { + "External id": 1410645,"Record function id": 0, "Ev Idx": 3156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263909.126, "dur": 2.572, + "args": { + "External id": 1410646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263909.770, "dur": 1.472, + "args": { + "External id": 1410647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263910.175, "dur": 0.960, + "args": { + "External id": 1410648,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263916.244, "dur": 4.577, + "args": { + "External id": 1410649,"Record function id": 0, "Ev Idx": 3160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263917.576, "dur": 2.732, + "args": { + "External id": 1410650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263918.351, "dur": 1.495, + "args": { + "External id": 1410651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263918.942, "dur": 0.784, + "args": { + "External id": 1410652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263924.760, "dur": 5.061, + "args": { + "External id": 1410653,"Record function id": 0, "Ev Idx": 3164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263926.562, "dur": 2.791, + "args": { + "External id": 1410654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263927.242, "dur": 1.604, + "args": { + "External id": 1410655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263927.975, "dur": 0.724, + "args": { + "External id": 1410656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263933.722, "dur": 7.174, + "args": { + "External id": 1410657,"Record function id": 0, "Ev Idx": 3168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263935.222, "dur": 5.209, + "args": { + "External id": 1410658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263936.008, "dur": 3.789, + "args": { + "External id": 1410659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263938.910, "dur": 0.780, + "args": { + "External id": 1410660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263944.898, "dur": 4.535, + "args": { + "External id": 1410661,"Record function id": 0, "Ev Idx": 3172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263946.300, "dur": 2.688, + "args": { + "External id": 1410662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263947.023, "dur": 1.475, + "args": { + "External id": 1410663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263947.442, "dur": 0.920, + "args": { + "External id": 1410664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263953.242, "dur": 4.713, + "args": { + "External id": 1410665,"Record function id": 0, "Ev Idx": 3176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532263954.624, "dur": 2.759, + "args": { + "External id": 1410666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263955.532, "dur": 1.252, + "args": { + "External id": 1410667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532263955.982, "dur": 0.680, + "args": { + "External id": 1410668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532263962.852, "dur": 61778.397, + "args": { + "External id": 1410669,"Record function id": 0, "Sequence number": 15108875, "Fwd thread id": 1, "Ev Idx": 3180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532263964.224, "dur": 61763.095, + "args": { + "External id": 1410670,"Sequence number": 15108875, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3181 + } + }, + { + "ph": "f", "id": 191, "pid": 2338710, "tid": 2379450, "ts": 6410532263964.224, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410532264000.347, "dur": 44.398, + "args": { + "External id": 1410671,"Record function id": 0, "Ev Idx": 3182 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410532264054.718, "dur": 119.488, + "args": { + "External id": 1410672,"Record function id": 0, "Ev Idx": 3183 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410532264183.735, "dur": 61531.261, + "args": { + "External id": 1410673,"Record function id": 0, "Ev Idx": 3184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532264289.814, "dur": 8.859, + "args": { + "External id": 1410674,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532264311.229, "dur": 7.835, + "args": { + "External id": 1410675,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532264337.316, "dur": 60339.753, + "args": { + "External id": 1410676,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532264354.938, "dur": 60306.411, + "args": { + "External id": 1410677,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532264497.462, "dur": 26.041, + "args": { + "External id": 1410678,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532264551.573, "dur": 60043.130, + "args": { + "External id": 1410679,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532264555.007, "dur": 60038.163, + "args": { + "External id": 1410680,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532264560.626, "dur": 13.541, + "args": { + "External id": 1410681,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532264577.047, "dur": 60008.727, + "args": { + "External id": 1410682,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532324829.544, "dur": 19.392, + "args": { + "External id": 1410683,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532324835.509, "dur": 12.682, + "args": { + "External id": 1410684,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532324894.956, "dur": 405.985, + "args": { + "External id": 1410685,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532324935.540, "dur": 356.706, + "args": { + "External id": 1410686,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3197, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532324954.820, "dur": 328.168, + "args": { + "External id": 1410687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532325334.866, "dur": 3.170, + "args": { + "External id": 1410688,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3199, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325449.147, "dur": 8.788, + "args": { + "External id": 1410689,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325513.889, "dur": 1.737, + "args": { + "External id": 1410690,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325535.211, "dur": 3.620, + "args": { + "External id": 1410691,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325553.066, "dur": 1.185, + "args": { + "External id": 1410692,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325567.782, "dur": 1.348, + "args": { + "External id": 1410693,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325581.503, "dur": 0.986, + "args": { + "External id": 1410694,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325594.970, "dur": 3.435, + "args": { + "External id": 1410695,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325611.152, "dur": 3.750, + "args": { + "External id": 1410696,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532325626.937, "dur": 1.332, + "args": { + "External id": 1410697,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532325763.439, "dur": 3685.291, + "args": { + "External id": 1410698,"Record function id": 0, "Ev Idx": 3209 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410532325792.509, "dur": 1533.502, + "args": { + "External id": 1410699,"Record function id": 0, "Ev Idx": 3210 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410532325815.327, "dur": 590.683, + "args": { + "External id": 1410700,"Record function id": 0, "Ev Idx": 3211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532325973.770, "dur": 7.674, + "args": { + "External id": 1410701,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532325987.974, "dur": 1.763, + "args": { + "External id": 1410702,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532325993.137, "dur": 4.326, + "args": { + "External id": 1410703,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532326000.499, "dur": 1.946, + "args": { + "External id": 1410704,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532326005.601, "dur": 1.762, + "args": { + "External id": 1410705,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532326010.801, "dur": 2.130, + "args": { + "External id": 1410706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532326016.237, "dur": 3.703, + "args": { + "External id": 1410707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532326023.073, "dur": 1.373, + "args": { + "External id": 1410708,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532326027.771, "dur": 1.517, + "args": { + "External id": 1410709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532326032.475, "dur": 1.402, + "args": { + "External id": 1410710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532326105.419, "dur": 246.528, + "args": { + "External id": 1410711,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532326152.556, "dur": 191.202, + "args": { + "External id": 1410712,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532326176.153, "dur": 25.788, + "args": { + "External id": 1410713,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532326207.730, "dur": 94.632, + "args": { + "External id": 1410714,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532326211.576, "dur": 90.293, + "args": { + "External id": 1410715,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326218.139, "dur": 8.802, + "args": { + "External id": 1410716,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532326229.526, "dur": 71.650, + "args": { + "External id": 1410717,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3228 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.14", "pid": 2338710, "tid": 2379450, + "ts": 6410532326556.917, "dur": 759.449, + "args": { + "External id": 1410718,"Record function id": 0, "Ev Idx": 3229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410532326584.173, "dur": 715.539, + "args": { + "External id": 1410719,"Record function id": 0, "Ev Idx": 3230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532326668.817, "dur": 8.149, + "args": { + "External id": 1410720,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532326695.870, "dur": 38.864, + "args": { + "External id": 1410721,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326702.104, "dur": 2.398, + "args": { + "External id": 1410722,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326707.357, "dur": 0.521, + "args": { + "External id": 1410723,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326709.739, "dur": 0.568, + "args": { + "External id": 1410724,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326712.154, "dur": 0.658, + "args": { + "External id": 1410725,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326715.135, "dur": 0.632, + "args": { + "External id": 1410726,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326717.326, "dur": 3.255, + "args": { + "External id": 1410727,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326722.283, "dur": 0.454, + "args": { + "External id": 1410728,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326724.431, "dur": 0.458, + "args": { + "External id": 1410729,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326726.558, "dur": 0.460, + "args": { + "External id": 1410730,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532326747.338, "dur": 57.383, + "args": { + "External id": 1410731,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532326845.044, "dur": 130.926, + "args": { + "External id": 1410732,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532326858.033, "dur": 4.222, + "args": { + "External id": 1410733,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532326868.519, "dur": 12.613, + "args": { + "External id": 1410734,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532326873.966, "dur": 6.660, + "args": { + "External id": 1410735,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326878.082, "dur": 0.860, + "args": { + "External id": 1410736,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532326889.550, "dur": 32.188, + "args": { + "External id": 1410737,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326892.299, "dur": 0.566, + "args": { + "External id": 1410738,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326894.822, "dur": 0.503, + "args": { + "External id": 1410739,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326897.258, "dur": 2.918, + "args": { + "External id": 1410740,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326902.452, "dur": 0.426, + "args": { + "External id": 1410741,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326905.036, "dur": 0.434, + "args": { + "External id": 1410742,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326907.168, "dur": 0.547, + "args": { + "External id": 1410743,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326909.673, "dur": 0.376, + "args": { + "External id": 1410744,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326912.043, "dur": 0.513, + "args": { + "External id": 1410745,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532326914.394, "dur": 0.414, + "args": { + "External id": 1410746,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532326933.476, "dur": 33.738, + "args": { + "External id": 1410747,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532327032.058, "dur": 179.103, + "args": { + "External id": 1410748,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532327097.057, "dur": 109.391, + "args": { + "External id": 1410749,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3260, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532327110.885, "dur": 90.049, + "args": { + "External id": 1410750,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532327227.945, "dur": 2.409, + "args": { + "External id": 1410751,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3262, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532327334.505, "dur": 2072.271, + "args": { + "External id": 1410752,"Sequence number": 15108874, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3263 + } + }, + { + "ph": "f", "id": 192, "pid": 2338710, "tid": 2379450, "ts": 6410532327334.505, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532327484.636, "dur": 123.777, + "args": { + "External id": 1410753,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532327654.286, "dur": 46.280, + "args": { + "External id": 1410754,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532327722.569, "dur": 59.471, + "args": { + "External id": 1410755,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532327795.324, "dur": 38.059, + "args": { + "External id": 1410756,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532327841.493, "dur": 37.425, + "args": { + "External id": 1410757,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532327886.988, "dur": 32.295, + "args": { + "External id": 1410758,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532327930.440, "dur": 33.029, + "args": { + "External id": 1410759,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532327996.257, "dur": 26.500, + "args": { + "External id": 1410760,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532328042.847, "dur": 74.951, + "args": { + "External id": 1410761,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532328146.962, "dur": 23.676, + "args": { + "External id": 1410762,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532328186.475, "dur": 34.380, + "args": { + "External id": 1410763,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532328241.486, "dur": 60.668, + "args": { + "External id": 1410764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532328306.669, "dur": 41.740, + "args": { + "External id": 1410765,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532328388.510, "dur": 311.358, + "args": { + "External id": 1410766,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532328505.310, "dur": 7.927, + "args": { + "External id": 1410767,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532328516.196, "dur": 2.799, + "args": { + "External id": 1410768,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532328520.600, "dur": 2.505, + "args": { + "External id": 1410769,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532328524.422, "dur": 2.373, + "args": { + "External id": 1410770,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532328577.662, "dur": 5.809, + "args": { + "External id": 1410771,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532328579.957, "dur": 3.331, + "args": { + "External id": 1410772,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532328585.906, "dur": 37.713, + "args": { + "External id": 1410773,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532328591.781, "dur": 4.481, + "args": { + "External id": 1410774,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532328625.714, "dur": 2.614, + "args": { + "External id": 1410775,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532328627.399, "dur": 0.852, + "args": { + "External id": 1410776,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532328630.125, "dur": 17.023, + "args": { + "External id": 1410777,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532328632.035, "dur": 0.557, + "args": { + "External id": 1410778,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532328744.378, "dur": 34.304, + "args": { + "External id": 1410779,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532328796.707, "dur": 20.105, + "args": { + "External id": 1410780,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532328826.756, "dur": 55.264, + "args": { + "External id": 1410781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532328890.852, "dur": 46.130, + "args": { + "External id": 1410782,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532328949.612, "dur": 26.811, + "args": { + "External id": 1410783,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532328983.576, "dur": 36.295, + "args": { + "External id": 1410784,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532329029.282, "dur": 75.040, + "args": { + "External id": 1410785,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532329118.070, "dur": 42.498, + "args": { + "External id": 1410786,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532329184.368, "dur": 30.911, + "args": { + "External id": 1410787,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532329234.189, "dur": 30.629, + "args": { + "External id": 1410788,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532329281.022, "dur": 21.750, + "args": { + "External id": 1410789,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532329320.646, "dur": 18.122, + "args": { + "External id": 1410790,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532329352.687, "dur": 19.677, + "args": { + "External id": 1410791,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329474.791, "dur": 18.255, + "args": { + "External id": 1410792,"Record function id": 0, "Ev Idx": 3303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329478.867, "dur": 13.052, + "args": { + "External id": 1410793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329483.897, "dur": 6.833, + "args": { + "External id": 1410794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329485.903, "dur": 4.673, + "args": { + "External id": 1410795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329497.885, "dur": 5.977, + "args": { + "External id": 1410796,"Record function id": 0, "Ev Idx": 3307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329499.313, "dur": 3.974, + "args": { + "External id": 1410797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329500.459, "dur": 2.244, + "args": { + "External id": 1410798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329501.390, "dur": 1.187, + "args": { + "External id": 1410799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329507.763, "dur": 7.111, + "args": { + "External id": 1410800,"Record function id": 0, "Ev Idx": 3311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329509.037, "dur": 5.335, + "args": { + "External id": 1410801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329509.603, "dur": 4.275, + "args": { + "External id": 1410802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329509.966, "dur": 3.829, + "args": { + "External id": 1410803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329518.683, "dur": 4.519, + "args": { + "External id": 1410804,"Record function id": 0, "Ev Idx": 3315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329519.925, "dur": 2.777, + "args": { + "External id": 1410805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329520.549, "dur": 1.643, + "args": { + "External id": 1410806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329521.259, "dur": 0.848, + "args": { + "External id": 1410807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329527.030, "dur": 4.791, + "args": { + "External id": 1410808,"Record function id": 0, "Ev Idx": 3319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329528.343, "dur": 2.964, + "args": { + "External id": 1410809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329529.145, "dur": 1.642, + "args": { + "External id": 1410810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329529.970, "dur": 0.731, + "args": { + "External id": 1410811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329535.830, "dur": 4.213, + "args": { + "External id": 1410812,"Record function id": 0, "Ev Idx": 3323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329536.917, "dur": 2.655, + "args": { + "External id": 1410813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329537.605, "dur": 1.418, + "args": { + "External id": 1410814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329538.184, "dur": 0.677, + "args": { + "External id": 1410815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329543.817, "dur": 4.236, + "args": { + "External id": 1410816,"Record function id": 0, "Ev Idx": 3327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329545.121, "dur": 2.456, + "args": { + "External id": 1410817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329545.855, "dur": 1.249, + "args": { + "External id": 1410818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329546.200, "dur": 0.790, + "args": { + "External id": 1410819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329551.838, "dur": 4.435, + "args": { + "External id": 1410820,"Record function id": 0, "Ev Idx": 3331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329553.143, "dur": 2.649, + "args": { + "External id": 1410821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329554.049, "dur": 1.182, + "args": { + "External id": 1410822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329554.390, "dur": 0.733, + "args": { + "External id": 1410823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329560.042, "dur": 4.235, + "args": { + "External id": 1410824,"Record function id": 0, "Ev Idx": 3335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532329561.177, "dur": 2.635, + "args": { + "External id": 1410825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329561.812, "dur": 1.524, + "args": { + "External id": 1410826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532329562.531, "dur": 0.692, + "args": { + "External id": 1410827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532329568.914, "dur": 61130.886, + "args": { + "External id": 1410828,"Record function id": 0, "Sequence number": 15108873, "Fwd thread id": 1, "Ev Idx": 3339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532329570.571, "dur": 61119.248, + "args": { + "External id": 1410829,"Sequence number": 15108873, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3340 + } + }, + { + "ph": "f", "id": 193, "pid": 2338710, "tid": 2379450, "ts": 6410532329570.571, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410532329606.268, "dur": 47.467, + "args": { + "External id": 1410830,"Record function id": 0, "Ev Idx": 3341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410532329662.906, "dur": 72.797, + "args": { + "External id": 1410831,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410532329742.806, "dur": 60937.597, + "args": { + "External id": 1410832,"Record function id": 0, "Ev Idx": 3343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532329860.921, "dur": 11.503, + "args": { + "External id": 1410833,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532329886.095, "dur": 7.813, + "args": { + "External id": 1410834,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532329919.315, "dur": 59684.016, + "args": { + "External id": 1410835,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532329938.965, "dur": 59649.608, + "args": { + "External id": 1410836,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532330151.196, "dur": 31.764, + "args": { + "External id": 1410837,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532330213.787, "dur": 59312.544, + "args": { + "External id": 1410838,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532330217.983, "dur": 59307.005, + "args": { + "External id": 1410839,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532330227.056, "dur": 17.775, + "args": { + "External id": 1410840,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532330248.363, "dur": 59271.075, + "args": { + "External id": 1410841,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532389734.719, "dur": 15.261, + "args": { + "External id": 1410842,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532389739.104, "dur": 10.302, + "args": { + "External id": 1410843,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532389788.676, "dur": 505.696, + "args": { + "External id": 1410844,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532389820.982, "dur": 466.400, + "args": { + "External id": 1410845,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3356, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532389834.230, "dur": 446.263, + "args": { + "External id": 1410846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532390319.333, "dur": 2.656, + "args": { + "External id": 1410847,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3358, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390397.321, "dur": 8.340, + "args": { + "External id": 1410848,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390482.301, "dur": 2.868, + "args": { + "External id": 1410849,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390504.182, "dur": 3.716, + "args": { + "External id": 1410850,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390522.482, "dur": 1.100, + "args": { + "External id": 1410851,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390535.962, "dur": 1.015, + "args": { + "External id": 1410852,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390549.302, "dur": 1.380, + "args": { + "External id": 1410853,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390563.158, "dur": 3.112, + "args": { + "External id": 1410854,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390587.323, "dur": 3.779, + "args": { + "External id": 1410855,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390603.992, "dur": 1.254, + "args": { + "External id": 1410856,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532390718.597, "dur": 3467.145, + "args": { + "External id": 1410857,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410532390741.916, "dur": 1283.722, + "args": { + "External id": 1410858,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410532390760.630, "dur": 439.102, + "args": { + "External id": 1410859,"Record function id": 0, "Ev Idx": 3370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390869.738, "dur": 5.002, + "args": { + "External id": 1410860,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390878.716, "dur": 1.053, + "args": { + "External id": 1410861,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390882.066, "dur": 3.532, + "args": { + "External id": 1410862,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390887.853, "dur": 1.400, + "args": { + "External id": 1410863,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390890.914, "dur": 1.356, + "args": { + "External id": 1410864,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390894.130, "dur": 1.189, + "args": { + "External id": 1410865,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390897.277, "dur": 2.486, + "args": { + "External id": 1410866,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390901.537, "dur": 1.064, + "args": { + "External id": 1410867,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390904.683, "dur": 0.960, + "args": { + "External id": 1410868,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532390907.548, "dur": 0.950, + "args": { + "External id": 1410869,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532390928.979, "dur": 227.990, + "args": { + "External id": 1410870,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532390948.468, "dur": 201.762, + "args": { + "External id": 1410871,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532390967.044, "dur": 17.935, + "args": { + "External id": 1410872,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532390989.390, "dur": 123.216, + "args": { + "External id": 1410873,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532390992.935, "dur": 119.130, + "args": { + "External id": 1410874,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532390998.034, "dur": 6.359, + "args": { + "External id": 1410875,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532391006.552, "dur": 104.085, + "args": { + "External id": 1410876,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.13", "pid": 2338710, "tid": 2379450, + "ts": 6410532391314.914, "dur": 701.164, + "args": { + "External id": 1410877,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410532391335.082, "dur": 664.902, + "args": { + "External id": 1410878,"Record function id": 0, "Ev Idx": 3389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532391409.188, "dur": 24.341, + "args": { + "External id": 1410879,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532391455.210, "dur": 42.628, + "args": { + "External id": 1410880,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391466.182, "dur": 1.953, + "args": { + "External id": 1410881,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391471.200, "dur": 0.575, + "args": { + "External id": 1410882,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391473.623, "dur": 0.386, + "args": { + "External id": 1410883,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391476.071, "dur": 0.592, + "args": { + "External id": 1410884,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391478.493, "dur": 0.575, + "args": { + "External id": 1410885,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391481.184, "dur": 2.650, + "args": { + "External id": 1410886,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391485.958, "dur": 0.506, + "args": { + "External id": 1410887,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391488.166, "dur": 0.675, + "args": { + "External id": 1410888,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391490.483, "dur": 0.554, + "args": { + "External id": 1410889,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532391510.998, "dur": 57.373, + "args": { + "External id": 1410890,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532391607.426, "dur": 134.679, + "args": { + "External id": 1410891,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532391620.762, "dur": 4.576, + "args": { + "External id": 1410892,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532391631.480, "dur": 11.833, + "args": { + "External id": 1410893,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532391636.553, "dur": 6.296, + "args": { + "External id": 1410894,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391640.705, "dur": 0.600, + "args": { + "External id": 1410895,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532391651.630, "dur": 30.415, + "args": { + "External id": 1410896,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391654.527, "dur": 0.513, + "args": { + "External id": 1410897,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391657.213, "dur": 0.424, + "args": { + "External id": 1410898,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391659.569, "dur": 3.118, + "args": { + "External id": 1410899,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391664.428, "dur": 0.453, + "args": { + "External id": 1410900,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391666.706, "dur": 0.592, + "args": { + "External id": 1410901,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391669.189, "dur": 0.360, + "args": { + "External id": 1410902,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391671.557, "dur": 0.420, + "args": { + "External id": 1410903,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391673.628, "dur": 0.430, + "args": { + "External id": 1410904,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532391675.537, "dur": 0.654, + "args": { + "External id": 1410905,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532391696.627, "dur": 35.421, + "args": { + "External id": 1410906,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532391796.764, "dur": 127.562, + "args": { + "External id": 1410907,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532391822.312, "dur": 97.660, + "args": { + "External id": 1410908,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3419, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532391833.613, "dur": 81.369, + "args": { + "External id": 1410909,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532391938.792, "dur": 2.166, + "args": { + "External id": 1410910,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3421, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532392033.554, "dur": 2127.239, + "args": { + "External id": 1410911,"Sequence number": 15108872, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3422 + } + }, + { + "ph": "f", "id": 194, "pid": 2338710, "tid": 2379450, "ts": 6410532392033.554, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532392213.550, "dur": 126.422, + "args": { + "External id": 1410912,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532392384.023, "dur": 68.730, + "args": { + "External id": 1410913,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532392478.866, "dur": 66.033, + "args": { + "External id": 1410914,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532392559.420, "dur": 39.381, + "args": { + "External id": 1410915,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532392608.214, "dur": 38.572, + "args": { + "External id": 1410916,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532392655.262, "dur": 35.560, + "args": { + "External id": 1410917,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532392699.217, "dur": 36.314, + "args": { + "External id": 1410918,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532392766.543, "dur": 28.896, + "args": { + "External id": 1410919,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532392819.212, "dur": 30.951, + "args": { + "External id": 1410920,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532392873.279, "dur": 22.164, + "args": { + "External id": 1410921,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532392912.834, "dur": 15.950, + "args": { + "External id": 1410922,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532392939.423, "dur": 45.261, + "args": { + "External id": 1410923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532392989.681, "dur": 37.318, + "args": { + "External id": 1410924,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532393102.483, "dur": 345.658, + "args": { + "External id": 1410925,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532393196.868, "dur": 19.966, + "args": { + "External id": 1410926,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532393224.054, "dur": 3.698, + "args": { + "External id": 1410927,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532393229.126, "dur": 2.463, + "args": { + "External id": 1410928,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532393233.052, "dur": 2.318, + "args": { + "External id": 1410929,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532393296.039, "dur": 6.130, + "args": { + "External id": 1410930,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532393298.679, "dur": 3.328, + "args": { + "External id": 1410931,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532393304.819, "dur": 42.469, + "args": { + "External id": 1410932,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532393311.298, "dur": 7.689, + "args": { + "External id": 1410933,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532393349.299, "dur": 2.195, + "args": { + "External id": 1410934,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532393350.694, "dur": 0.725, + "args": { + "External id": 1410935,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532393353.365, "dur": 16.506, + "args": { + "External id": 1410936,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532393355.316, "dur": 0.674, + "args": { + "External id": 1410937,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532393497.240, "dur": 37.459, + "args": { + "External id": 1410938,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532393555.796, "dur": 18.503, + "args": { + "External id": 1410939,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532393585.015, "dur": 61.711, + "args": { + "External id": 1410940,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532393655.928, "dur": 48.967, + "args": { + "External id": 1410941,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532393717.563, "dur": 24.809, + "args": { + "External id": 1410942,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532393750.443, "dur": 36.541, + "args": { + "External id": 1410943,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532393796.689, "dur": 31.573, + "args": { + "External id": 1410944,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532393837.133, "dur": 35.412, + "args": { + "External id": 1410945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532393895.023, "dur": 30.808, + "args": { + "External id": 1410946,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532393944.725, "dur": 29.793, + "args": { + "External id": 1410947,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532393992.239, "dur": 19.717, + "args": { + "External id": 1410948,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532394030.716, "dur": 16.537, + "args": { + "External id": 1410949,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532394099.473, "dur": 23.645, + "args": { + "External id": 1410950,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394211.368, "dur": 18.723, + "args": { + "External id": 1410951,"Record function id": 0, "Ev Idx": 3462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394215.872, "dur": 13.114, + "args": { + "External id": 1410952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394220.872, "dur": 7.142, + "args": { + "External id": 1410953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394223.228, "dur": 4.607, + "args": { + "External id": 1410954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394234.860, "dur": 6.397, + "args": { + "External id": 1410955,"Record function id": 0, "Ev Idx": 3466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394236.759, "dur": 3.976, + "args": { + "External id": 1410956,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394237.788, "dur": 2.388, + "args": { + "External id": 1410957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394238.776, "dur": 1.276, + "args": { + "External id": 1410958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394245.244, "dur": 6.848, + "args": { + "External id": 1410959,"Record function id": 0, "Ev Idx": 3470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394246.439, "dur": 5.124, + "args": { + "External id": 1410960,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394247.031, "dur": 3.920, + "args": { + "External id": 1410961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394247.448, "dur": 3.401, + "args": { + "External id": 1410962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394255.903, "dur": 4.803, + "args": { + "External id": 1410963,"Record function id": 0, "Ev Idx": 3474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394257.499, "dur": 2.727, + "args": { + "External id": 1410964,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394258.074, "dur": 1.584, + "args": { + "External id": 1410965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394258.444, "dur": 1.134, + "args": { + "External id": 1410966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394264.283, "dur": 4.760, + "args": { + "External id": 1410967,"Record function id": 0, "Ev Idx": 3478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394265.842, "dur": 2.694, + "args": { + "External id": 1410968,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394266.692, "dur": 1.326, + "args": { + "External id": 1410969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394267.034, "dur": 0.869, + "args": { + "External id": 1410970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394273.121, "dur": 5.495, + "args": { + "External id": 1410971,"Record function id": 0, "Ev Idx": 3482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394274.782, "dur": 3.368, + "args": { + "External id": 1410972,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394275.648, "dur": 2.005, + "args": { + "External id": 1410973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394276.412, "dur": 1.126, + "args": { + "External id": 1410974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394282.490, "dur": 4.546, + "args": { + "External id": 1410975,"Record function id": 0, "Ev Idx": 3486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394283.813, "dur": 2.737, + "args": { + "External id": 1410976,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394284.581, "dur": 1.273, + "args": { + "External id": 1410977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394285.063, "dur": 0.666, + "args": { + "External id": 1410978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394290.749, "dur": 4.344, + "args": { + "External id": 1410979,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394292.009, "dur": 2.632, + "args": { + "External id": 1410980,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394292.547, "dur": 1.476, + "args": { + "External id": 1410981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394293.063, "dur": 0.857, + "args": { + "External id": 1410982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394298.697, "dur": 4.446, + "args": { + "External id": 1410983,"Record function id": 0, "Ev Idx": 3494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532394299.969, "dur": 2.687, + "args": { + "External id": 1410984,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394300.504, "dur": 1.537, + "args": { + "External id": 1410985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532394301.123, "dur": 0.806, + "args": { + "External id": 1410986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532394307.746, "dur": 63373.628, + "args": { + "External id": 1410987,"Record function id": 0, "Sequence number": 15108871, "Fwd thread id": 1, "Ev Idx": 3498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532394309.379, "dur": 63361.483, + "args": { + "External id": 1410988,"Sequence number": 15108871, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3499 + } + }, + { + "ph": "f", "id": 195, "pid": 2338710, "tid": 2379450, "ts": 6410532394309.379, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410532394346.529, "dur": 44.742, + "args": { + "External id": 1410989,"Record function id": 0, "Ev Idx": 3500 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410532394404.120, "dur": 94.125, + "args": { + "External id": 1410990,"Record function id": 0, "Ev Idx": 3501 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410532394508.088, "dur": 63153.825, + "args": { + "External id": 1410991,"Record function id": 0, "Ev Idx": 3502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532394623.994, "dur": 8.788, + "args": { + "External id": 1410992,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532394645.029, "dur": 8.137, + "args": { + "External id": 1410993,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532394670.183, "dur": 61932.967, + "args": { + "External id": 1410994,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532394686.583, "dur": 61901.314, + "args": { + "External id": 1410995,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532394819.683, "dur": 20.291, + "args": { + "External id": 1410996,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532394863.924, "dur": 61663.923, + "args": { + "External id": 1410997,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532394867.284, "dur": 61659.086, + "args": { + "External id": 1410998,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532394872.666, "dur": 10.137, + "args": { + "External id": 1410999,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532394885.601, "dur": 61633.308, + "args": { + "External id": 1411000,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532456734.834, "dur": 16.093, + "args": { + "External id": 1411001,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532456739.947, "dur": 10.408, + "args": { + "External id": 1411002,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532456789.464, "dur": 485.275, + "args": { + "External id": 1411003,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532456822.482, "dur": 445.480, + "args": { + "External id": 1411004,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3515, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532456836.836, "dur": 422.643, + "args": { + "External id": 1411005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532457300.691, "dur": 2.604, + "args": { + "External id": 1411006,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3517, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457376.311, "dur": 8.351, + "args": { + "External id": 1411007,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457459.245, "dur": 2.529, + "args": { + "External id": 1411008,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457482.683, "dur": 7.422, + "args": { + "External id": 1411009,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457504.913, "dur": 1.319, + "args": { + "External id": 1411010,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457520.039, "dur": 1.047, + "args": { + "External id": 1411011,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457533.895, "dur": 1.109, + "args": { + "External id": 1411012,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457551.344, "dur": 3.064, + "args": { + "External id": 1411013,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457567.576, "dur": 2.822, + "args": { + "External id": 1411014,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457583.740, "dur": 1.492, + "args": { + "External id": 1411015,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532457699.512, "dur": 4271.861, + "args": { + "External id": 1411016,"Record function id": 0, "Ev Idx": 3527 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410532457722.566, "dur": 1311.818, + "args": { + "External id": 1411017,"Record function id": 0, "Ev Idx": 3528 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410532457741.296, "dur": 450.804, + "args": { + "External id": 1411018,"Record function id": 0, "Ev Idx": 3529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457853.522, "dur": 5.277, + "args": { + "External id": 1411019,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457863.014, "dur": 1.158, + "args": { + "External id": 1411020,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457866.241, "dur": 3.201, + "args": { + "External id": 1411021,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457871.448, "dur": 1.353, + "args": { + "External id": 1411022,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457874.535, "dur": 1.225, + "args": { + "External id": 1411023,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457877.720, "dur": 0.936, + "args": { + "External id": 1411024,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457880.390, "dur": 2.754, + "args": { + "External id": 1411025,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457884.857, "dur": 0.919, + "args": { + "External id": 1411026,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457887.570, "dur": 0.884, + "args": { + "External id": 1411027,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532457890.124, "dur": 1.223, + "args": { + "External id": 1411028,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532457910.691, "dur": 238.511, + "args": { + "External id": 1411029,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532457929.792, "dur": 212.275, + "args": { + "External id": 1411030,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532457956.651, "dur": 19.201, + "args": { + "External id": 1411031,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532457980.451, "dur": 123.302, + "args": { + "External id": 1411032,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532457983.916, "dur": 119.351, + "args": { + "External id": 1411033,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532457988.278, "dur": 6.270, + "args": { + "External id": 1411034,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532457996.905, "dur": 104.826, + "args": { + "External id": 1411035,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.12", "pid": 2338710, "tid": 2379450, + "ts": 6410532458304.801, "dur": 719.055, + "args": { + "External id": 1411036,"Record function id": 0, "Ev Idx": 3547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410532458326.708, "dur": 682.123, + "args": { + "External id": 1411037,"Record function id": 0, "Ev Idx": 3548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532458403.076, "dur": 7.659, + "args": { + "External id": 1411038,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532458447.544, "dur": 42.458, + "args": { + "External id": 1411039,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458453.311, "dur": 2.332, + "args": { + "External id": 1411040,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458458.446, "dur": 0.504, + "args": { + "External id": 1411041,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458461.062, "dur": 0.553, + "args": { + "External id": 1411042,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458463.440, "dur": 0.445, + "args": { + "External id": 1411043,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458465.910, "dur": 0.436, + "args": { + "External id": 1411044,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458468.103, "dur": 2.602, + "args": { + "External id": 1411045,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458472.735, "dur": 0.387, + "args": { + "External id": 1411046,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458481.483, "dur": 0.484, + "args": { + "External id": 1411047,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458483.736, "dur": 0.457, + "args": { + "External id": 1411048,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532458505.722, "dur": 55.053, + "args": { + "External id": 1411049,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532458600.798, "dur": 133.338, + "args": { + "External id": 1411050,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532458617.649, "dur": 5.747, + "args": { + "External id": 1411051,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532458629.622, "dur": 12.402, + "args": { + "External id": 1411052,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532458634.781, "dur": 6.767, + "args": { + "External id": 1411053,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458639.254, "dur": 0.909, + "args": { + "External id": 1411054,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532458649.931, "dur": 27.546, + "args": { + "External id": 1411055,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458652.476, "dur": 0.538, + "args": { + "External id": 1411056,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458654.949, "dur": 0.536, + "args": { + "External id": 1411057,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458657.242, "dur": 2.548, + "args": { + "External id": 1411058,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458661.582, "dur": 0.550, + "args": { + "External id": 1411059,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458664.285, "dur": 0.477, + "args": { + "External id": 1411060,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458666.545, "dur": 0.531, + "args": { + "External id": 1411061,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458669.051, "dur": 0.396, + "args": { + "External id": 1411062,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458670.857, "dur": 0.390, + "args": { + "External id": 1411063,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532458672.822, "dur": 0.394, + "args": { + "External id": 1411064,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532458688.900, "dur": 35.869, + "args": { + "External id": 1411065,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532458795.525, "dur": 134.131, + "args": { + "External id": 1411066,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532458822.419, "dur": 102.975, + "args": { + "External id": 1411067,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3578, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532458837.576, "dur": 83.248, + "args": { + "External id": 1411068,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532458946.889, "dur": 2.178, + "args": { + "External id": 1411069,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3580, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532459042.960, "dur": 2899.679, + "args": { + "External id": 1411070,"Sequence number": 15108870, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3581 + } + }, + { + "ph": "f", "id": 196, "pid": 2338710, "tid": 2379450, "ts": 6410532459042.960, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532459242.380, "dur": 125.913, + "args": { + "External id": 1411071,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532459414.218, "dur": 64.688, + "args": { + "External id": 1411072,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532459548.179, "dur": 67.392, + "args": { + "External id": 1411073,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532459630.354, "dur": 37.651, + "args": { + "External id": 1411074,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532459676.227, "dur": 37.758, + "args": { + "External id": 1411075,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532459722.964, "dur": 32.846, + "args": { + "External id": 1411076,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532459764.423, "dur": 33.833, + "args": { + "External id": 1411077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532459829.825, "dur": 27.706, + "args": { + "External id": 1411078,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532459877.520, "dur": 31.139, + "args": { + "External id": 1411079,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532459931.747, "dur": 22.151, + "args": { + "External id": 1411080,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532459968.260, "dur": 16.991, + "args": { + "External id": 1411081,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532459995.814, "dur": 44.027, + "args": { + "External id": 1411082,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532460044.617, "dur": 102.076, + "args": { + "External id": 1411083,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532460212.085, "dur": 346.892, + "args": { + "External id": 1411084,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532460329.316, "dur": 8.136, + "args": { + "External id": 1411085,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532460340.292, "dur": 3.113, + "args": { + "External id": 1411086,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532460345.052, "dur": 2.509, + "args": { + "External id": 1411087,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532460349.072, "dur": 1.849, + "args": { + "External id": 1411088,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532460410.161, "dur": 22.527, + "args": { + "External id": 1411089,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532460412.316, "dur": 19.616, + "args": { + "External id": 1411090,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532460436.157, "dur": 44.109, + "args": { + "External id": 1411091,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532460443.451, "dur": 4.421, + "args": { + "External id": 1411092,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532460482.301, "dur": 2.162, + "args": { + "External id": 1411093,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532460483.471, "dur": 0.871, + "args": { + "External id": 1411094,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532460485.810, "dur": 19.202, + "args": { + "External id": 1411095,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532460488.512, "dur": 0.560, + "args": { + "External id": 1411096,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532460611.514, "dur": 47.166, + "args": { + "External id": 1411097,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532460689.029, "dur": 28.764, + "args": { + "External id": 1411098,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532460733.210, "dur": 95.072, + "args": { + "External id": 1411099,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532460844.021, "dur": 80.303, + "args": { + "External id": 1411100,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532460944.400, "dur": 278.388, + "args": { + "External id": 1411101,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532461455.133, "dur": 67.528, + "args": { + "External id": 1411102,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532461540.031, "dur": 40.635, + "args": { + "External id": 1411103,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532461590.417, "dur": 37.732, + "args": { + "External id": 1411104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532461662.979, "dur": 40.492, + "args": { + "External id": 1411105,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532461724.955, "dur": 33.863, + "args": { + "External id": 1411106,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532461777.137, "dur": 22.117, + "args": { + "External id": 1411107,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532461819.767, "dur": 20.389, + "args": { + "External id": 1411108,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532461864.716, "dur": 30.049, + "args": { + "External id": 1411109,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532461998.231, "dur": 19.400, + "args": { + "External id": 1411110,"Record function id": 0, "Ev Idx": 3621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462002.197, "dur": 14.339, + "args": { + "External id": 1411111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462007.364, "dur": 7.938, + "args": { + "External id": 1411112,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462009.785, "dur": 5.341, + "args": { + "External id": 1411113,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462022.197, "dur": 9.929, + "args": { + "External id": 1411114,"Record function id": 0, "Ev Idx": 3625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462023.835, "dur": 7.767, + "args": { + "External id": 1411115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462025.012, "dur": 5.964, + "args": { + "External id": 1411116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462026.254, "dur": 4.512, + "args": { + "External id": 1411117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462036.089, "dur": 8.497, + "args": { + "External id": 1411118,"Record function id": 0, "Ev Idx": 3629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462038.002, "dur": 6.108, + "args": { + "External id": 1411119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462038.780, "dur": 4.675, + "args": { + "External id": 1411120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462039.500, "dur": 3.872, + "args": { + "External id": 1411121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462048.307, "dur": 5.236, + "args": { + "External id": 1411122,"Record function id": 0, "Ev Idx": 3633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462049.894, "dur": 3.142, + "args": { + "External id": 1411123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462050.928, "dur": 1.586, + "args": { + "External id": 1411124,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462051.575, "dur": 0.837, + "args": { + "External id": 1411125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462099.686, "dur": 8.779, + "args": { + "External id": 1411126,"Record function id": 0, "Ev Idx": 3637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462102.369, "dur": 5.333, + "args": { + "External id": 1411127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462104.090, "dur": 2.608, + "args": { + "External id": 1411128,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462104.849, "dur": 1.592, + "args": { + "External id": 1411129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462112.852, "dur": 5.488, + "args": { + "External id": 1411130,"Record function id": 0, "Ev Idx": 3641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462114.177, "dur": 3.686, + "args": { + "External id": 1411131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462115.049, "dur": 2.230, + "args": { + "External id": 1411132,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462116.262, "dur": 0.886, + "args": { + "External id": 1411133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462122.066, "dur": 4.746, + "args": { + "External id": 1411134,"Record function id": 0, "Ev Idx": 3645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462123.591, "dur": 2.729, + "args": { + "External id": 1411135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462124.353, "dur": 1.398, + "args": { + "External id": 1411136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462124.887, "dur": 0.747, + "args": { + "External id": 1411137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462130.721, "dur": 4.259, + "args": { + "External id": 1411138,"Record function id": 0, "Ev Idx": 3649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462132.050, "dur": 2.453, + "args": { + "External id": 1411139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462132.631, "dur": 1.269, + "args": { + "External id": 1411140,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462133.028, "dur": 0.792, + "args": { + "External id": 1411141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462138.662, "dur": 4.470, + "args": { + "External id": 1411142,"Record function id": 0, "Ev Idx": 3653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532462140.045, "dur": 2.584, + "args": { + "External id": 1411143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462140.705, "dur": 1.440, + "args": { + "External id": 1411144,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532462141.395, "dur": 0.642, + "args": { + "External id": 1411145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532462147.732, "dur": 60438.535, + "args": { + "External id": 1411146,"Record function id": 0, "Sequence number": 15108869, "Fwd thread id": 1, "Ev Idx": 3657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532462149.386, "dur": 60426.104, + "args": { + "External id": 1411147,"Sequence number": 15108869, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3658 + } + }, + { + "ph": "f", "id": 197, "pid": 2338710, "tid": 2379450, "ts": 6410532462149.386, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410532462185.769, "dur": 48.018, + "args": { + "External id": 1411148,"Record function id": 0, "Ev Idx": 3659 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410532462244.168, "dur": 79.874, + "args": { + "External id": 1411149,"Record function id": 0, "Ev Idx": 3660 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410532462330.595, "dur": 60236.019, + "args": { + "External id": 1411150,"Record function id": 0, "Ev Idx": 3661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532462466.626, "dur": 10.302, + "args": { + "External id": 1411151,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532462490.502, "dur": 8.560, + "args": { + "External id": 1411152,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532462519.190, "dur": 58945.891, + "args": { + "External id": 1411153,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532462538.730, "dur": 58910.655, + "args": { + "External id": 1411154,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532462667.550, "dur": 20.333, + "args": { + "External id": 1411155,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532462711.537, "dur": 58665.244, + "args": { + "External id": 1411156,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532462715.057, "dur": 58659.934, + "args": { + "External id": 1411157,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532462720.381, "dur": 10.929, + "args": { + "External id": 1411158,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532462734.267, "dur": 58633.077, + "args": { + "External id": 1411159,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532521595.116, "dur": 16.296, + "args": { + "External id": 1411160,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532521600.180, "dur": 10.853, + "args": { + "External id": 1411161,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532521647.970, "dur": 537.832, + "args": { + "External id": 1411162,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532521680.686, "dur": 497.903, + "args": { + "External id": 1411163,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3674, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532521694.632, "dur": 477.169, + "args": { + "External id": 1411164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532522215.902, "dur": 3.304, + "args": { + "External id": 1411165,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3676, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522295.376, "dur": 8.431, + "args": { + "External id": 1411166,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522357.187, "dur": 1.888, + "args": { + "External id": 1411167,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522376.905, "dur": 3.523, + "args": { + "External id": 1411168,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522394.307, "dur": 1.435, + "args": { + "External id": 1411169,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522409.367, "dur": 1.172, + "args": { + "External id": 1411170,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522443.527, "dur": 1.901, + "args": { + "External id": 1411171,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522459.928, "dur": 3.101, + "args": { + "External id": 1411172,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522475.059, "dur": 2.338, + "args": { + "External id": 1411173,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522489.610, "dur": 1.150, + "args": { + "External id": 1411174,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532522605.481, "dur": 3539.953, + "args": { + "External id": 1411175,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410532522628.761, "dur": 1330.956, + "args": { + "External id": 1411176,"Record function id": 0, "Ev Idx": 3687 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410532522645.576, "dur": 453.836, + "args": { + "External id": 1411177,"Record function id": 0, "Ev Idx": 3688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522747.219, "dur": 4.817, + "args": { + "External id": 1411178,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522756.194, "dur": 1.459, + "args": { + "External id": 1411179,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522759.576, "dur": 3.893, + "args": { + "External id": 1411180,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522765.438, "dur": 0.949, + "args": { + "External id": 1411181,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522768.056, "dur": 1.251, + "args": { + "External id": 1411182,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522771.164, "dur": 1.145, + "args": { + "External id": 1411183,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522774.206, "dur": 2.363, + "args": { + "External id": 1411184,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522778.456, "dur": 1.035, + "args": { + "External id": 1411185,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522781.021, "dur": 1.062, + "args": { + "External id": 1411186,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532522783.574, "dur": 0.920, + "args": { + "External id": 1411187,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532522804.171, "dur": 211.727, + "args": { + "External id": 1411188,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532522845.908, "dur": 164.143, + "args": { + "External id": 1411189,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532522863.837, "dur": 18.807, + "args": { + "External id": 1411190,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532522887.424, "dur": 85.930, + "args": { + "External id": 1411191,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532522890.616, "dur": 82.236, + "args": { + "External id": 1411192,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532522895.490, "dur": 6.371, + "args": { + "External id": 1411193,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532522904.173, "dur": 67.741, + "args": { + "External id": 1411194,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.11", "pid": 2338710, "tid": 2379450, + "ts": 6410532523217.803, "dur": 732.507, + "args": { + "External id": 1411195,"Record function id": 0, "Ev Idx": 3706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410532523240.159, "dur": 694.623, + "args": { + "External id": 1411196,"Record function id": 0, "Ev Idx": 3707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532523318.468, "dur": 7.182, + "args": { + "External id": 1411197,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532523343.053, "dur": 38.061, + "args": { + "External id": 1411198,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523349.382, "dur": 1.903, + "args": { + "External id": 1411199,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523353.822, "dur": 0.474, + "args": { + "External id": 1411200,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523356.684, "dur": 0.584, + "args": { + "External id": 1411201,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523359.337, "dur": 0.633, + "args": { + "External id": 1411202,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523362.366, "dur": 0.528, + "args": { + "External id": 1411203,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523364.729, "dur": 3.155, + "args": { + "External id": 1411204,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523369.705, "dur": 0.520, + "args": { + "External id": 1411205,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523371.773, "dur": 0.483, + "args": { + "External id": 1411206,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523374.106, "dur": 0.397, + "args": { + "External id": 1411207,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532523393.395, "dur": 76.303, + "args": { + "External id": 1411208,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532523517.302, "dur": 144.768, + "args": { + "External id": 1411209,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532523531.268, "dur": 5.609, + "args": { + "External id": 1411210,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532523543.869, "dur": 13.404, + "args": { + "External id": 1411211,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532523549.085, "dur": 7.676, + "args": { + "External id": 1411212,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523553.716, "dur": 0.842, + "args": { + "External id": 1411213,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532523565.256, "dur": 31.680, + "args": { + "External id": 1411214,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523567.962, "dur": 0.727, + "args": { + "External id": 1411215,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523573.940, "dur": 0.550, + "args": { + "External id": 1411216,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523576.302, "dur": 2.349, + "args": { + "External id": 1411217,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523580.243, "dur": 0.486, + "args": { + "External id": 1411218,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523582.462, "dur": 0.458, + "args": { + "External id": 1411219,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523584.434, "dur": 0.555, + "args": { + "External id": 1411220,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523586.828, "dur": 0.414, + "args": { + "External id": 1411221,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523589.156, "dur": 0.560, + "args": { + "External id": 1411222,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532523591.496, "dur": 0.402, + "args": { + "External id": 1411223,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532523611.302, "dur": 41.722, + "args": { + "External id": 1411224,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532523718.986, "dur": 136.043, + "args": { + "External id": 1411225,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532523748.476, "dur": 102.239, + "args": { + "External id": 1411226,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3737, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532523760.116, "dur": 85.886, + "args": { + "External id": 1411227,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532523872.401, "dur": 2.107, + "args": { + "External id": 1411228,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3739, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532523968.408, "dur": 2150.504, + "args": { + "External id": 1411229,"Sequence number": 15108868, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3740 + } + }, + { + "ph": "f", "id": 198, "pid": 2338710, "tid": 2379450, "ts": 6410532523968.408, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532524146.622, "dur": 127.355, + "args": { + "External id": 1411230,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532524320.657, "dur": 50.791, + "args": { + "External id": 1411231,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532524393.783, "dur": 82.454, + "args": { + "External id": 1411232,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532524494.592, "dur": 42.589, + "args": { + "External id": 1411233,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532524546.431, "dur": 40.018, + "args": { + "External id": 1411234,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532524595.648, "dur": 34.417, + "args": { + "External id": 1411235,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532524638.438, "dur": 35.060, + "args": { + "External id": 1411236,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532524705.054, "dur": 31.056, + "args": { + "External id": 1411237,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532524756.669, "dur": 34.544, + "args": { + "External id": 1411238,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532524814.669, "dur": 23.428, + "args": { + "External id": 1411239,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532524851.755, "dur": 18.114, + "args": { + "External id": 1411240,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532524880.282, "dur": 46.864, + "args": { + "External id": 1411241,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532524931.355, "dur": 39.437, + "args": { + "External id": 1411242,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532525016.706, "dur": 376.176, + "args": { + "External id": 1411243,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532525179.632, "dur": 10.467, + "args": { + "External id": 1411244,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532525193.177, "dur": 3.691, + "args": { + "External id": 1411245,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532525198.482, "dur": 2.036, + "args": { + "External id": 1411246,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532525201.681, "dur": 1.904, + "args": { + "External id": 1411247,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532525267.795, "dur": 5.756, + "args": { + "External id": 1411248,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532525270.061, "dur": 3.302, + "args": { + "External id": 1411249,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532525275.894, "dur": 40.980, + "args": { + "External id": 1411250,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532525282.231, "dur": 4.264, + "args": { + "External id": 1411251,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532525318.689, "dur": 2.292, + "args": { + "External id": 1411252,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532525320.124, "dur": 0.776, + "args": { + "External id": 1411253,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532525322.052, "dur": 18.352, + "args": { + "External id": 1411254,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532525324.290, "dur": 0.718, + "args": { + "External id": 1411255,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532525453.342, "dur": 37.031, + "args": { + "External id": 1411256,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532525510.673, "dur": 21.656, + "args": { + "External id": 1411257,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532525542.588, "dur": 62.035, + "args": { + "External id": 1411258,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532525613.483, "dur": 48.174, + "args": { + "External id": 1411259,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532525673.496, "dur": 27.743, + "args": { + "External id": 1411260,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532525708.722, "dur": 37.814, + "args": { + "External id": 1411261,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532525755.972, "dur": 36.427, + "args": { + "External id": 1411262,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532525801.033, "dur": 35.542, + "args": { + "External id": 1411263,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532525857.407, "dur": 28.500, + "args": { + "External id": 1411264,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532525908.192, "dur": 30.350, + "args": { + "External id": 1411265,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532525957.824, "dur": 20.429, + "args": { + "External id": 1411266,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532525996.719, "dur": 16.455, + "args": { + "External id": 1411267,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532526026.559, "dur": 18.082, + "args": { + "External id": 1411268,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526171.847, "dur": 18.443, + "args": { + "External id": 1411269,"Record function id": 0, "Ev Idx": 3780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526175.969, "dur": 13.184, + "args": { + "External id": 1411270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526181.207, "dur": 6.786, + "args": { + "External id": 1411271,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526183.337, "dur": 4.491, + "args": { + "External id": 1411272,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526195.163, "dur": 5.970, + "args": { + "External id": 1411273,"Record function id": 0, "Ev Idx": 3784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526196.530, "dur": 4.088, + "args": { + "External id": 1411274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526197.640, "dur": 2.360, + "args": { + "External id": 1411275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526198.635, "dur": 1.201, + "args": { + "External id": 1411276,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526204.948, "dur": 7.254, + "args": { + "External id": 1411277,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526206.068, "dur": 5.592, + "args": { + "External id": 1411278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526206.666, "dur": 4.484, + "args": { + "External id": 1411279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526207.198, "dur": 3.855, + "args": { + "External id": 1411280,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526216.017, "dur": 4.811, + "args": { + "External id": 1411281,"Record function id": 0, "Ev Idx": 3792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526217.544, "dur": 2.809, + "args": { + "External id": 1411282,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526218.234, "dur": 1.649, + "args": { + "External id": 1411283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526218.707, "dur": 1.099, + "args": { + "External id": 1411284,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526224.518, "dur": 7.636, + "args": { + "External id": 1411285,"Record function id": 0, "Ev Idx": 3796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526225.916, "dur": 5.082, + "args": { + "External id": 1411286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526227.611, "dur": 2.515, + "args": { + "External id": 1411287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526228.330, "dur": 1.651, + "args": { + "External id": 1411288,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526237.938, "dur": 8.020, + "args": { + "External id": 1411289,"Record function id": 0, "Ev Idx": 3800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526240.365, "dur": 4.792, + "args": { + "External id": 1411290,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526241.798, "dur": 2.449, + "args": { + "External id": 1411291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526242.899, "dur": 1.074, + "args": { + "External id": 1411292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526251.695, "dur": 7.747, + "args": { + "External id": 1411293,"Record function id": 0, "Ev Idx": 3804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526253.936, "dur": 4.749, + "args": { + "External id": 1411294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526255.356, "dur": 2.599, + "args": { + "External id": 1411295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526256.139, "dur": 1.612, + "args": { + "External id": 1411296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526265.011, "dur": 8.411, + "args": { + "External id": 1411297,"Record function id": 0, "Ev Idx": 3808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526267.636, "dur": 4.998, + "args": { + "External id": 1411298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526269.398, "dur": 2.584, + "args": { + "External id": 1411299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526270.149, "dur": 1.684, + "args": { + "External id": 1411300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526279.066, "dur": 7.342, + "args": { + "External id": 1411301,"Record function id": 0, "Ev Idx": 3812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532526281.318, "dur": 4.302, + "args": { + "External id": 1411302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526282.478, "dur": 2.441, + "args": { + "External id": 1411303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532526283.568, "dur": 1.132, + "args": { + "External id": 1411304,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532526292.863, "dur": 61907.110, + "args": { + "External id": 1411305,"Record function id": 0, "Sequence number": 15108867, "Fwd thread id": 1, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532526295.231, "dur": 61894.937, + "args": { + "External id": 1411306,"Sequence number": 15108867, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3817 + } + }, + { + "ph": "f", "id": 199, "pid": 2338710, "tid": 2379450, "ts": 6410532526295.231, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410532526337.194, "dur": 55.134, + "args": { + "External id": 1411307,"Record function id": 0, "Ev Idx": 3818 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410532526404.453, "dur": 135.454, + "args": { + "External id": 1411308,"Record function id": 0, "Ev Idx": 3819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410532526554.945, "dur": 61625.821, + "args": { + "External id": 1411309,"Record function id": 0, "Ev Idx": 3820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532527143.347, "dur": 17.122, + "args": { + "External id": 1411310,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532527179.438, "dur": 10.935, + "args": { + "External id": 1411311,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532527214.050, "dur": 59948.215, + "args": { + "External id": 1411312,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532527231.576, "dur": 59915.871, + "args": { + "External id": 1411313,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532527345.361, "dur": 22.642, + "args": { + "External id": 1411314,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532527392.002, "dur": 59695.211, + "args": { + "External id": 1411315,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532527395.358, "dur": 59690.712, + "args": { + "External id": 1411316,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532527400.777, "dur": 12.440, + "args": { + "External id": 1411317,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532527434.345, "dur": 59646.612, + "args": { + "External id": 1411318,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532587289.951, "dur": 15.674, + "args": { + "External id": 1411319,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532587294.287, "dur": 10.879, + "args": { + "External id": 1411320,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532587345.964, "dur": 431.244, + "args": { + "External id": 1411321,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532587377.764, "dur": 393.027, + "args": { + "External id": 1411322,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3833, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532587391.895, "dur": 372.693, + "args": { + "External id": 1411323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532587801.598, "dur": 2.811, + "args": { + "External id": 1411324,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3835, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532587876.421, "dur": 7.807, + "args": { + "External id": 1411325,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532587939.503, "dur": 1.975, + "args": { + "External id": 1411326,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532587959.728, "dur": 3.427, + "args": { + "External id": 1411327,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532587976.915, "dur": 1.148, + "args": { + "External id": 1411328,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532587991.173, "dur": 1.175, + "args": { + "External id": 1411329,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588004.526, "dur": 1.203, + "args": { + "External id": 1411330,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588018.224, "dur": 3.329, + "args": { + "External id": 1411331,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588034.066, "dur": 2.684, + "args": { + "External id": 1411332,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588048.334, "dur": 1.028, + "args": { + "External id": 1411333,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532588219.060, "dur": 3439.416, + "args": { + "External id": 1411334,"Record function id": 0, "Ev Idx": 3845 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410532588242.283, "dur": 1317.584, + "args": { + "External id": 1411335,"Record function id": 0, "Ev Idx": 3846 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410532588261.259, "dur": 421.114, + "args": { + "External id": 1411336,"Record function id": 0, "Ev Idx": 3847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588371.462, "dur": 5.639, + "args": { + "External id": 1411337,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588380.886, "dur": 1.336, + "args": { + "External id": 1411338,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588384.704, "dur": 3.052, + "args": { + "External id": 1411339,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588389.558, "dur": 1.206, + "args": { + "External id": 1411340,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588392.489, "dur": 0.924, + "args": { + "External id": 1411341,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588395.154, "dur": 1.042, + "args": { + "External id": 1411342,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588398.200, "dur": 2.489, + "args": { + "External id": 1411343,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588402.333, "dur": 1.204, + "args": { + "External id": 1411344,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588405.189, "dur": 1.050, + "args": { + "External id": 1411345,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532588408.182, "dur": 1.067, + "args": { + "External id": 1411346,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532588448.143, "dur": 193.538, + "args": { + "External id": 1411347,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532588471.899, "dur": 163.662, + "args": { + "External id": 1411348,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532588498.293, "dur": 17.879, + "args": { + "External id": 1411349,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532588524.143, "dur": 78.820, + "args": { + "External id": 1411350,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532588527.197, "dur": 75.306, + "args": { + "External id": 1411351,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588531.169, "dur": 7.287, + "args": { + "External id": 1411352,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532588540.693, "dur": 61.164, + "args": { + "External id": 1411353,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.10", "pid": 2338710, "tid": 2379450, + "ts": 6410532588792.490, "dur": 757.470, + "args": { + "External id": 1411354,"Record function id": 0, "Ev Idx": 3865 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410532588813.193, "dur": 721.064, + "args": { + "External id": 1411355,"Record function id": 0, "Ev Idx": 3866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532588888.537, "dur": 6.307, + "args": { + "External id": 1411356,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532588911.527, "dur": 34.696, + "args": { + "External id": 1411357,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588917.344, "dur": 1.890, + "args": { + "External id": 1411358,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588922.017, "dur": 0.497, + "args": { + "External id": 1411359,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588924.436, "dur": 0.429, + "args": { + "External id": 1411360,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588926.666, "dur": 0.590, + "args": { + "External id": 1411361,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588928.744, "dur": 0.505, + "args": { + "External id": 1411362,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588930.893, "dur": 2.551, + "args": { + "External id": 1411363,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588935.279, "dur": 0.534, + "args": { + "External id": 1411364,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588937.492, "dur": 0.594, + "args": { + "External id": 1411365,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532588939.729, "dur": 0.596, + "args": { + "External id": 1411366,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532588957.926, "dur": 49.898, + "args": { + "External id": 1411367,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532589046.824, "dur": 184.339, + "args": { + "External id": 1411368,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532589100.904, "dur": 6.534, + "args": { + "External id": 1411369,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532589115.003, "dur": 13.989, + "args": { + "External id": 1411370,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532589120.418, "dur": 8.004, + "args": { + "External id": 1411371,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589125.173, "dur": 1.101, + "args": { + "External id": 1411372,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532589137.626, "dur": 33.099, + "args": { + "External id": 1411373,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589140.377, "dur": 0.587, + "args": { + "External id": 1411374,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589142.976, "dur": 0.510, + "args": { + "External id": 1411375,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589150.498, "dur": 2.530, + "args": { + "External id": 1411376,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589154.642, "dur": 0.449, + "args": { + "External id": 1411377,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589156.597, "dur": 0.602, + "args": { + "External id": 1411378,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589159.284, "dur": 0.440, + "args": { + "External id": 1411379,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589161.319, "dur": 0.703, + "args": { + "External id": 1411380,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589163.618, "dur": 0.308, + "args": { + "External id": 1411381,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532589165.618, "dur": 0.485, + "args": { + "External id": 1411382,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532589184.147, "dur": 37.477, + "args": { + "External id": 1411383,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532589289.917, "dur": 150.656, + "args": { + "External id": 1411384,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532589319.893, "dur": 115.731, + "args": { + "External id": 1411385,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3896, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532589331.337, "dur": 82.443, + "args": { + "External id": 1411386,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532589464.965, "dur": 2.747, + "args": { + "External id": 1411387,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3898, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532589569.661, "dur": 2062.952, + "args": { + "External id": 1411388,"Sequence number": 15108866, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3899 + } + }, + { + "ph": "f", "id": 200, "pid": 2338710, "tid": 2379450, "ts": 6410532589569.661, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532589702.264, "dur": 124.347, + "args": { + "External id": 1411389,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532589874.939, "dur": 46.790, + "args": { + "External id": 1411390,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532589942.353, "dur": 55.315, + "args": { + "External id": 1411391,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532590010.990, "dur": 35.640, + "args": { + "External id": 1411392,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532590054.082, "dur": 85.144, + "args": { + "External id": 1411393,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532590151.049, "dur": 35.809, + "args": { + "External id": 1411394,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532590194.471, "dur": 35.407, + "args": { + "External id": 1411395,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532590264.078, "dur": 31.875, + "args": { + "External id": 1411396,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532590316.631, "dur": 35.453, + "args": { + "External id": 1411397,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532590377.093, "dur": 24.619, + "args": { + "External id": 1411398,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532590434.713, "dur": 24.221, + "args": { + "External id": 1411399,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532590472.268, "dur": 48.646, + "args": { + "External id": 1411400,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532590525.489, "dur": 38.094, + "args": { + "External id": 1411401,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532590597.959, "dur": 309.513, + "args": { + "External id": 1411402,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532590692.712, "dur": 6.999, + "args": { + "External id": 1411403,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532590701.767, "dur": 3.007, + "args": { + "External id": 1411404,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532590706.267, "dur": 2.209, + "args": { + "External id": 1411405,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532590709.606, "dur": 1.928, + "args": { + "External id": 1411406,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532590756.410, "dur": 18.854, + "args": { + "External id": 1411407,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532590761.032, "dur": 12.628, + "args": { + "External id": 1411408,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532590780.158, "dur": 44.807, + "args": { + "External id": 1411409,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532590787.853, "dur": 4.053, + "args": { + "External id": 1411410,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532590827.184, "dur": 1.933, + "args": { + "External id": 1411411,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532590828.202, "dur": 0.838, + "args": { + "External id": 1411412,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532590830.289, "dur": 16.444, + "args": { + "External id": 1411413,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532590832.683, "dur": 0.766, + "args": { + "External id": 1411414,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532590954.570, "dur": 31.739, + "args": { + "External id": 1411415,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532591006.967, "dur": 17.727, + "args": { + "External id": 1411416,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532591033.480, "dur": 89.721, + "args": { + "External id": 1411417,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532591133.852, "dur": 49.465, + "args": { + "External id": 1411418,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532591196.495, "dur": 25.680, + "args": { + "External id": 1411419,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532591229.473, "dur": 35.988, + "args": { + "External id": 1411420,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532591274.680, "dur": 33.369, + "args": { + "External id": 1411421,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532591316.447, "dur": 36.236, + "args": { + "External id": 1411422,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532591378.431, "dur": 28.658, + "args": { + "External id": 1411423,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532591446.308, "dur": 33.110, + "args": { + "External id": 1411424,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532591500.452, "dur": 22.191, + "args": { + "External id": 1411425,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532591541.674, "dur": 21.708, + "args": { + "External id": 1411426,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532591581.203, "dur": 18.893, + "args": { + "External id": 1411427,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591683.848, "dur": 17.954, + "args": { + "External id": 1411428,"Record function id": 0, "Ev Idx": 3939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591687.672, "dur": 12.888, + "args": { + "External id": 1411429,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591692.539, "dur": 6.826, + "args": { + "External id": 1411430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591694.298, "dur": 4.851, + "args": { + "External id": 1411431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591706.404, "dur": 5.739, + "args": { + "External id": 1411432,"Record function id": 0, "Ev Idx": 3943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591707.924, "dur": 3.480, + "args": { + "External id": 1411433,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591708.872, "dur": 1.833, + "args": { + "External id": 1411434,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591709.525, "dur": 1.086, + "args": { + "External id": 1411435,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591716.201, "dur": 7.412, + "args": { + "External id": 1411436,"Record function id": 0, "Ev Idx": 3947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591717.807, "dur": 5.278, + "args": { + "External id": 1411437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591718.605, "dur": 3.845, + "args": { + "External id": 1411438,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591719.310, "dur": 3.057, + "args": { + "External id": 1411439,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591727.500, "dur": 5.020, + "args": { + "External id": 1411440,"Record function id": 0, "Ev Idx": 3951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591729.124, "dur": 2.813, + "args": { + "External id": 1411441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591729.795, "dur": 1.596, + "args": { + "External id": 1411442,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591730.379, "dur": 0.886, + "args": { + "External id": 1411443,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591736.322, "dur": 4.430, + "args": { + "External id": 1411444,"Record function id": 0, "Ev Idx": 3955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591737.631, "dur": 2.585, + "args": { + "External id": 1411445,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591738.451, "dur": 1.258, + "args": { + "External id": 1411446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591738.824, "dur": 0.800, + "args": { + "External id": 1411447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591744.470, "dur": 4.856, + "args": { + "External id": 1411448,"Record function id": 0, "Ev Idx": 3959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591745.885, "dur": 2.891, + "args": { + "External id": 1411449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591746.563, "dur": 1.723, + "args": { + "External id": 1411450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591746.996, "dur": 1.164, + "args": { + "External id": 1411451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591753.268, "dur": 13.401, + "args": { + "External id": 1411452,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591754.787, "dur": 11.270, + "args": { + "External id": 1411453,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591755.417, "dur": 10.050, + "args": { + "External id": 1411454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591764.634, "dur": 0.742, + "args": { + "External id": 1411455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591770.459, "dur": 4.980, + "args": { + "External id": 1411456,"Record function id": 0, "Ev Idx": 3967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591771.828, "dur": 3.101, + "args": { + "External id": 1411457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591772.613, "dur": 1.743, + "args": { + "External id": 1411458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591773.098, "dur": 1.141, + "args": { + "External id": 1411459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591779.149, "dur": 7.026, + "args": { + "External id": 1411460,"Record function id": 0, "Ev Idx": 3971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532591780.425, "dur": 5.109, + "args": { + "External id": 1411461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591781.244, "dur": 3.803, + "args": { + "External id": 1411462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532591784.187, "dur": 0.720, + "args": { + "External id": 1411463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532591790.856, "dur": 63429.868, + "args": { + "External id": 1411464,"Record function id": 0, "Sequence number": 15108865, "Fwd thread id": 1, "Ev Idx": 3975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532591792.431, "dur": 63417.479, + "args": { + "External id": 1411465,"Sequence number": 15108865, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3976 + } + }, + { + "ph": "f", "id": 201, "pid": 2338710, "tid": 2379450, "ts": 6410532591792.431, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410532591824.784, "dur": 45.151, + "args": { + "External id": 1411466,"Record function id": 0, "Ev Idx": 3977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410532591879.536, "dur": 78.019, + "args": { + "External id": 1411467,"Record function id": 0, "Ev Idx": 3978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410532591969.523, "dur": 63230.679, + "args": { + "External id": 1411468,"Record function id": 0, "Ev Idx": 3979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532592117.701, "dur": 10.616, + "args": { + "External id": 1411469,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532592141.378, "dur": 7.876, + "args": { + "External id": 1411470,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532592166.362, "dur": 62017.521, + "args": { + "External id": 1411471,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532592183.427, "dur": 61984.402, + "args": { + "External id": 1411472,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532592300.359, "dur": 26.893, + "args": { + "External id": 1411473,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532592352.728, "dur": 61750.357, + "args": { + "External id": 1411474,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532592357.070, "dur": 61744.406, + "args": { + "External id": 1411475,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532592364.185, "dur": 16.380, + "args": { + "External id": 1411476,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532592383.875, "dur": 61710.506, + "args": { + "External id": 1411477,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532654310.572, "dur": 16.062, + "args": { + "External id": 1411478,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532654314.920, "dur": 11.171, + "args": { + "External id": 1411479,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532654364.701, "dur": 447.377, + "args": { + "External id": 1411480,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532654403.505, "dur": 402.563, + "args": { + "External id": 1411481,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3992, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532654432.245, "dur": 367.473, + "args": { + "External id": 1411482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532654840.428, "dur": 2.644, + "args": { + "External id": 1411483,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3994, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532654912.150, "dur": 8.378, + "args": { + "External id": 1411484,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532654973.397, "dur": 2.108, + "args": { + "External id": 1411485,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532654992.749, "dur": 3.752, + "args": { + "External id": 1411486,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655010.797, "dur": 0.999, + "args": { + "External id": 1411487,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655023.759, "dur": 1.114, + "args": { + "External id": 1411488,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655036.305, "dur": 1.227, + "args": { + "External id": 1411489,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655088.012, "dur": 4.721, + "args": { + "External id": 1411490,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655111.340, "dur": 2.966, + "args": { + "External id": 1411491,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655125.628, "dur": 0.822, + "args": { + "External id": 1411492,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532655240.303, "dur": 4234.686, + "args": { + "External id": 1411493,"Record function id": 0, "Ev Idx": 4004 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410532655263.566, "dur": 1324.898, + "args": { + "External id": 1411494,"Record function id": 0, "Ev Idx": 4005 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410532655279.693, "dur": 418.988, + "args": { + "External id": 1411495,"Record function id": 0, "Ev Idx": 4006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655389.501, "dur": 4.729, + "args": { + "External id": 1411496,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655398.020, "dur": 1.161, + "args": { + "External id": 1411497,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655401.395, "dur": 3.140, + "args": { + "External id": 1411498,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655406.421, "dur": 0.992, + "args": { + "External id": 1411499,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655409.141, "dur": 1.072, + "args": { + "External id": 1411500,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655413.905, "dur": 16.275, + "args": { + "External id": 1411501,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655435.206, "dur": 2.463, + "args": { + "External id": 1411502,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655439.395, "dur": 1.138, + "args": { + "External id": 1411503,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655442.043, "dur": 1.183, + "args": { + "External id": 1411504,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532655447.252, "dur": 1.129, + "args": { + "External id": 1411505,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532655472.448, "dur": 186.258, + "args": { + "External id": 1411506,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532655492.256, "dur": 160.438, + "args": { + "External id": 1411507,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532655514.188, "dur": 17.646, + "args": { + "External id": 1411508,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532655536.163, "dur": 78.264, + "args": { + "External id": 1411509,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532655539.388, "dur": 74.672, + "args": { + "External id": 1411510,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655544.125, "dur": 8.159, + "args": { + "External id": 1411511,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532655554.167, "dur": 59.156, + "args": { + "External id": 1411512,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4023 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.9", "pid": 2338710, "tid": 2379450, + "ts": 6410532655803.913, "dur": 774.564, + "args": { + "External id": 1411513,"Record function id": 0, "Ev Idx": 4024 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410532655824.721, "dur": 738.825, + "args": { + "External id": 1411514,"Record function id": 0, "Ev Idx": 4025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532655898.360, "dur": 5.872, + "args": { + "External id": 1411515,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532655921.023, "dur": 37.242, + "args": { + "External id": 1411516,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655927.108, "dur": 1.908, + "args": { + "External id": 1411517,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655931.363, "dur": 1.745, + "args": { + "External id": 1411518,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655935.174, "dur": 0.564, + "args": { + "External id": 1411519,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655937.333, "dur": 0.592, + "args": { + "External id": 1411520,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655940.743, "dur": 0.687, + "args": { + "External id": 1411521,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655943.139, "dur": 2.759, + "args": { + "External id": 1411522,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655947.921, "dur": 0.485, + "args": { + "External id": 1411523,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655950.871, "dur": 0.655, + "args": { + "External id": 1411524,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532655953.439, "dur": 0.441, + "args": { + "External id": 1411525,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532655970.461, "dur": 47.789, + "args": { + "External id": 1411526,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532656054.630, "dur": 193.425, + "args": { + "External id": 1411527,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532656109.221, "dur": 6.734, + "args": { + "External id": 1411528,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532656122.783, "dur": 13.185, + "args": { + "External id": 1411529,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532656127.662, "dur": 7.804, + "args": { + "External id": 1411530,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656132.531, "dur": 0.945, + "args": { + "External id": 1411531,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532656145.630, "dur": 28.556, + "args": { + "External id": 1411532,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656149.134, "dur": 0.531, + "args": { + "External id": 1411533,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656151.737, "dur": 0.391, + "args": { + "External id": 1411534,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656153.915, "dur": 2.489, + "args": { + "External id": 1411535,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656158.168, "dur": 0.787, + "args": { + "External id": 1411536,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656160.858, "dur": 0.552, + "args": { + "External id": 1411537,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656162.938, "dur": 0.488, + "args": { + "External id": 1411538,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656165.107, "dur": 0.555, + "args": { + "External id": 1411539,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656167.185, "dur": 0.457, + "args": { + "External id": 1411540,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532656169.254, "dur": 0.370, + "args": { + "External id": 1411541,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532656197.001, "dur": 41.138, + "args": { + "External id": 1411542,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532656306.821, "dur": 164.456, + "args": { + "External id": 1411543,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532656342.458, "dur": 124.409, + "args": { + "External id": 1411544,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4055, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532656357.215, "dur": 104.455, + "args": { + "External id": 1411545,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532656493.759, "dur": 2.655, + "args": { + "External id": 1411546,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4057, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532656598.962, "dur": 2846.293, + "args": { + "External id": 1411547,"Sequence number": 15108864, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4058 + } + }, + { + "ph": "f", "id": 202, "pid": 2338710, "tid": 2379450, "ts": 6410532656598.962, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532656732.394, "dur": 124.142, + "args": { + "External id": 1411548,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532656902.538, "dur": 48.583, + "args": { + "External id": 1411549,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532656971.652, "dur": 55.566, + "args": { + "External id": 1411550,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532657041.698, "dur": 96.928, + "args": { + "External id": 1411551,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532657152.195, "dur": 43.729, + "args": { + "External id": 1411552,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532657206.180, "dur": 31.212, + "args": { + "External id": 1411553,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532657246.884, "dur": 33.842, + "args": { + "External id": 1411554,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532657315.546, "dur": 28.735, + "args": { + "External id": 1411555,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532657365.696, "dur": 31.201, + "args": { + "External id": 1411556,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532657444.904, "dur": 24.790, + "args": { + "External id": 1411557,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532657487.369, "dur": 15.508, + "args": { + "External id": 1411558,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532657514.601, "dur": 46.330, + "args": { + "External id": 1411559,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532657565.440, "dur": 36.946, + "args": { + "External id": 1411560,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532657638.588, "dur": 314.414, + "args": { + "External id": 1411561,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532657728.647, "dur": 7.040, + "args": { + "External id": 1411562,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532657738.539, "dur": 4.249, + "args": { + "External id": 1411563,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532657744.414, "dur": 2.160, + "args": { + "External id": 1411564,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532657748.040, "dur": 1.825, + "args": { + "External id": 1411565,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532657814.550, "dur": 6.514, + "args": { + "External id": 1411566,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532657817.034, "dur": 3.502, + "args": { + "External id": 1411567,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532657823.367, "dur": 42.311, + "args": { + "External id": 1411568,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532657832.048, "dur": 4.550, + "args": { + "External id": 1411569,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532657869.142, "dur": 2.155, + "args": { + "External id": 1411570,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532657870.333, "dur": 0.817, + "args": { + "External id": 1411571,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532657872.544, "dur": 19.803, + "args": { + "External id": 1411572,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532657874.918, "dur": 2.219, + "args": { + "External id": 1411573,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532658002.088, "dur": 36.616, + "args": { + "External id": 1411574,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532658100.681, "dur": 25.471, + "args": { + "External id": 1411575,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532658137.767, "dur": 66.288, + "args": { + "External id": 1411576,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532658215.898, "dur": 67.657, + "args": { + "External id": 1411577,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532658300.768, "dur": 36.434, + "args": { + "External id": 1411578,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532658347.903, "dur": 58.412, + "args": { + "External id": 1411579,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532658443.489, "dur": 62.970, + "args": { + "External id": 1411580,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532658525.395, "dur": 52.738, + "args": { + "External id": 1411581,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532658620.096, "dur": 43.170, + "args": { + "External id": 1411582,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532658893.609, "dur": 280.258, + "args": { + "External id": 1411583,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532659210.732, "dur": 34.924, + "args": { + "External id": 1411584,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532659324.305, "dur": 22.506, + "args": { + "External id": 1411585,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532659367.394, "dur": 23.253, + "args": { + "External id": 1411586,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659503.244, "dur": 17.940, + "args": { + "External id": 1411587,"Record function id": 0, "Ev Idx": 4098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659507.336, "dur": 12.724, + "args": { + "External id": 1411588,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659512.558, "dur": 6.557, + "args": { + "External id": 1411589,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659514.125, "dur": 4.871, + "args": { + "External id": 1411590,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659525.748, "dur": 5.411, + "args": { + "External id": 1411591,"Record function id": 0, "Ev Idx": 4102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659527.645, "dur": 3.003, + "args": { + "External id": 1411592,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659528.627, "dur": 1.374, + "args": { + "External id": 1411593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659528.987, "dur": 0.924, + "args": { + "External id": 1411594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659535.045, "dur": 7.276, + "args": { + "External id": 1411595,"Record function id": 0, "Ev Idx": 4106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659536.395, "dur": 5.426, + "args": { + "External id": 1411596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659537.375, "dur": 3.974, + "args": { + "External id": 1411597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659538.041, "dur": 3.213, + "args": { + "External id": 1411598,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659546.099, "dur": 4.719, + "args": { + "External id": 1411599,"Record function id": 0, "Ev Idx": 4110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659547.882, "dur": 2.438, + "args": { + "External id": 1411600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659548.515, "dur": 1.308, + "args": { + "External id": 1411601,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659548.877, "dur": 0.873, + "args": { + "External id": 1411602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659554.497, "dur": 7.459, + "args": { + "External id": 1411603,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659556.782, "dur": 4.574, + "args": { + "External id": 1411604,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659557.343, "dur": 3.553, + "args": { + "External id": 1411605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659559.828, "dur": 0.903, + "args": { + "External id": 1411606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659565.633, "dur": 5.203, + "args": { + "External id": 1411607,"Record function id": 0, "Ev Idx": 4118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659567.496, "dur": 2.853, + "args": { + "External id": 1411608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659568.192, "dur": 1.595, + "args": { + "External id": 1411609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659568.751, "dur": 0.957, + "args": { + "External id": 1411610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659574.976, "dur": 4.437, + "args": { + "External id": 1411611,"Record function id": 0, "Ev Idx": 4122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659576.507, "dur": 2.444, + "args": { + "External id": 1411612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659577.261, "dur": 1.098, + "args": { + "External id": 1411613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659577.585, "dur": 0.697, + "args": { + "External id": 1411614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659583.138, "dur": 4.714, + "args": { + "External id": 1411615,"Record function id": 0, "Ev Idx": 4126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659584.728, "dur": 2.628, + "args": { + "External id": 1411616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659585.462, "dur": 1.402, + "args": { + "External id": 1411617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659586.074, "dur": 0.663, + "args": { + "External id": 1411618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659591.610, "dur": 6.061, + "args": { + "External id": 1411619,"Record function id": 0, "Ev Idx": 4130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532659592.919, "dur": 4.263, + "args": { + "External id": 1411620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659593.481, "dur": 3.241, + "args": { + "External id": 1411621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532659595.748, "dur": 0.860, + "args": { + "External id": 1411622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532659602.683, "dur": 62285.169, + "args": { + "External id": 1411623,"Record function id": 0, "Sequence number": 15108863, "Fwd thread id": 1, "Ev Idx": 4134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532659604.747, "dur": 62272.155, + "args": { + "External id": 1411624,"Sequence number": 15108863, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4135 + } + }, + { + "ph": "f", "id": 203, "pid": 2338710, "tid": 2379450, "ts": 6410532659604.747, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410532659655.130, "dur": 52.142, + "args": { + "External id": 1411625,"Record function id": 0, "Ev Idx": 4136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410532659717.773, "dur": 83.271, + "args": { + "External id": 1411626,"Record function id": 0, "Ev Idx": 4137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410532659810.030, "dur": 62057.873, + "args": { + "External id": 1411627,"Record function id": 0, "Ev Idx": 4138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532659918.691, "dur": 9.485, + "args": { + "External id": 1411628,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532659940.457, "dur": 7.399, + "args": { + "External id": 1411629,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532659963.905, "dur": 60916.962, + "args": { + "External id": 1411630,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532659980.495, "dur": 60884.860, + "args": { + "External id": 1411631,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532660132.147, "dur": 24.135, + "args": { + "External id": 1411632,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532660183.716, "dur": 60621.630, + "args": { + "External id": 1411633,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532660189.109, "dur": 60614.616, + "args": { + "External id": 1411634,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532660194.422, "dur": 11.937, + "args": { + "External id": 1411635,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532660210.851, "dur": 60587.156, + "args": { + "External id": 1411636,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532721014.214, "dur": 14.931, + "args": { + "External id": 1411637,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532721018.494, "dur": 10.177, + "args": { + "External id": 1411638,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532721101.602, "dur": 416.772, + "args": { + "External id": 1411639,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532721140.811, "dur": 371.185, + "args": { + "External id": 1411640,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4151, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532721155.912, "dur": 348.019, + "args": { + "External id": 1411641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532721545.715, "dur": 2.592, + "args": { + "External id": 1411642,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4153, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721621.917, "dur": 8.334, + "args": { + "External id": 1411643,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721683.367, "dur": 1.536, + "args": { + "External id": 1411644,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721704.743, "dur": 4.003, + "args": { + "External id": 1411645,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721721.989, "dur": 0.984, + "args": { + "External id": 1411646,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721737.143, "dur": 0.808, + "args": { + "External id": 1411647,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721749.676, "dur": 1.079, + "args": { + "External id": 1411648,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721763.343, "dur": 3.335, + "args": { + "External id": 1411649,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721779.561, "dur": 3.571, + "args": { + "External id": 1411650,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532721794.052, "dur": 0.995, + "args": { + "External id": 1411651,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532721906.085, "dur": 3544.800, + "args": { + "External id": 1411652,"Record function id": 0, "Ev Idx": 4163 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410532721931.263, "dur": 1347.600, + "args": { + "External id": 1411653,"Record function id": 0, "Ev Idx": 4164 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410532721948.841, "dur": 452.006, + "args": { + "External id": 1411654,"Record function id": 0, "Ev Idx": 4165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722097.497, "dur": 5.995, + "args": { + "External id": 1411655,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722108.256, "dur": 1.121, + "args": { + "External id": 1411656,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722111.592, "dur": 3.200, + "args": { + "External id": 1411657,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722116.904, "dur": 1.208, + "args": { + "External id": 1411658,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722123.348, "dur": 1.228, + "args": { + "External id": 1411659,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722126.536, "dur": 1.066, + "args": { + "External id": 1411660,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722130.194, "dur": 2.588, + "args": { + "External id": 1411661,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722137.370, "dur": 0.811, + "args": { + "External id": 1411662,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722144.531, "dur": 0.995, + "args": { + "External id": 1411663,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532722147.364, "dur": 1.050, + "args": { + "External id": 1411664,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532722171.480, "dur": 191.651, + "args": { + "External id": 1411665,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532722194.602, "dur": 163.063, + "args": { + "External id": 1411666,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532722213.217, "dur": 18.250, + "args": { + "External id": 1411667,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532722238.044, "dur": 81.947, + "args": { + "External id": 1411668,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532722241.274, "dur": 78.263, + "args": { + "External id": 1411669,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722246.253, "dur": 6.579, + "args": { + "External id": 1411670,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532722254.783, "dur": 63.955, + "args": { + "External id": 1411671,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4182 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.8", "pid": 2338710, "tid": 2379450, + "ts": 6410532722528.967, "dur": 741.127, + "args": { + "External id": 1411672,"Record function id": 0, "Ev Idx": 4183 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410532722549.893, "dur": 705.160, + "args": { + "External id": 1411673,"Record function id": 0, "Ev Idx": 4184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532722628.107, "dur": 7.140, + "args": { + "External id": 1411674,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532722653.147, "dur": 38.805, + "args": { + "External id": 1411675,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722659.393, "dur": 1.963, + "args": { + "External id": 1411676,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722664.218, "dur": 1.903, + "args": { + "External id": 1411677,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722667.760, "dur": 0.677, + "args": { + "External id": 1411678,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722670.484, "dur": 0.514, + "args": { + "External id": 1411679,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722673.756, "dur": 0.460, + "args": { + "External id": 1411680,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722675.967, "dur": 2.491, + "args": { + "External id": 1411681,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722679.953, "dur": 0.782, + "args": { + "External id": 1411682,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722682.952, "dur": 0.579, + "args": { + "External id": 1411683,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722685.214, "dur": 0.457, + "args": { + "External id": 1411684,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532722704.758, "dur": 59.912, + "args": { + "External id": 1411685,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532722801.519, "dur": 124.053, + "args": { + "External id": 1411686,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532722813.562, "dur": 4.567, + "args": { + "External id": 1411687,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532722824.224, "dur": 11.695, + "args": { + "External id": 1411688,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532722828.843, "dur": 6.575, + "args": { + "External id": 1411689,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722833.145, "dur": 0.893, + "args": { + "External id": 1411690,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532722844.423, "dur": 28.169, + "args": { + "External id": 1411691,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722846.795, "dur": 0.682, + "args": { + "External id": 1411692,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722850.127, "dur": 0.776, + "args": { + "External id": 1411693,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722852.230, "dur": 2.733, + "args": { + "External id": 1411694,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722856.699, "dur": 1.297, + "args": { + "External id": 1411695,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722859.978, "dur": 0.585, + "args": { + "External id": 1411696,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722862.058, "dur": 0.287, + "args": { + "External id": 1411697,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722864.194, "dur": 0.351, + "args": { + "External id": 1411698,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722866.076, "dur": 0.563, + "args": { + "External id": 1411699,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532722868.319, "dur": 0.286, + "args": { + "External id": 1411700,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532722885.126, "dur": 31.942, + "args": { + "External id": 1411701,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532722976.447, "dur": 184.816, + "args": { + "External id": 1411702,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532723009.250, "dur": 147.136, + "args": { + "External id": 1411703,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4214, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532723024.910, "dur": 125.589, + "args": { + "External id": 1411704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532723186.663, "dur": 2.330, + "args": { + "External id": 1411705,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4216, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532723286.953, "dur": 2122.378, + "args": { + "External id": 1411706,"Sequence number": 15108862, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4217 + } + }, + { + "ph": "f", "id": 204, "pid": 2338710, "tid": 2379450, "ts": 6410532723286.953, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532723434.002, "dur": 125.385, + "args": { + "External id": 1411707,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532723614.420, "dur": 49.823, + "args": { + "External id": 1411708,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532723685.236, "dur": 58.334, + "args": { + "External id": 1411709,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532723757.387, "dur": 37.691, + "args": { + "External id": 1411710,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532723802.975, "dur": 38.308, + "args": { + "External id": 1411711,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532723849.062, "dur": 38.004, + "args": { + "External id": 1411712,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532723895.684, "dur": 36.109, + "args": { + "External id": 1411713,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532723962.793, "dur": 31.647, + "args": { + "External id": 1411714,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532724019.067, "dur": 30.864, + "args": { + "External id": 1411715,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532724123.888, "dur": 27.352, + "args": { + "External id": 1411716,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532724167.621, "dur": 17.032, + "args": { + "External id": 1411717,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532724195.123, "dur": 52.847, + "args": { + "External id": 1411718,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532724252.583, "dur": 38.246, + "args": { + "External id": 1411719,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532724326.288, "dur": 351.146, + "args": { + "External id": 1411720,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532724449.655, "dur": 12.715, + "args": { + "External id": 1411721,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532724466.588, "dur": 3.104, + "args": { + "External id": 1411722,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532724471.158, "dur": 1.947, + "args": { + "External id": 1411723,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532724474.612, "dur": 1.782, + "args": { + "External id": 1411724,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532724535.421, "dur": 7.084, + "args": { + "External id": 1411725,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532724538.023, "dur": 4.272, + "args": { + "External id": 1411726,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532724544.811, "dur": 43.967, + "args": { + "External id": 1411727,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532724551.468, "dur": 8.172, + "args": { + "External id": 1411728,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532724592.876, "dur": 1.825, + "args": { + "External id": 1411729,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532724594.023, "dur": 0.560, + "args": { + "External id": 1411730,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532724595.950, "dur": 23.077, + "args": { + "External id": 1411731,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532724599.748, "dur": 0.767, + "args": { + "External id": 1411732,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532724723.963, "dur": 34.380, + "args": { + "External id": 1411733,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532724779.794, "dur": 20.067, + "args": { + "External id": 1411734,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532724809.456, "dur": 57.113, + "args": { + "External id": 1411735,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532724874.369, "dur": 46.327, + "args": { + "External id": 1411736,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532724931.823, "dur": 26.861, + "args": { + "External id": 1411737,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532724965.349, "dur": 35.373, + "args": { + "External id": 1411738,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532725009.493, "dur": 32.917, + "args": { + "External id": 1411739,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532725049.687, "dur": 78.281, + "args": { + "External id": 1411740,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532725156.119, "dur": 30.715, + "args": { + "External id": 1411741,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532725208.571, "dur": 33.393, + "args": { + "External id": 1411742,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532725263.513, "dur": 24.048, + "args": { + "External id": 1411743,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532725322.140, "dur": 18.328, + "args": { + "External id": 1411744,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532725357.123, "dur": 18.043, + "args": { + "External id": 1411745,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725477.631, "dur": 20.145, + "args": { + "External id": 1411746,"Record function id": 0, "Ev Idx": 4257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725481.644, "dur": 14.922, + "args": { + "External id": 1411747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725486.994, "dur": 8.065, + "args": { + "External id": 1411748,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725488.505, "dur": 6.438, + "args": { + "External id": 1411749,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725502.531, "dur": 5.239, + "args": { + "External id": 1411750,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725504.237, "dur": 2.979, + "args": { + "External id": 1411751,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725505.290, "dur": 1.323, + "args": { + "External id": 1411752,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725505.676, "dur": 0.834, + "args": { + "External id": 1411753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725511.682, "dur": 7.412, + "args": { + "External id": 1411754,"Record function id": 0, "Ev Idx": 4265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725513.195, "dur": 5.330, + "args": { + "External id": 1411755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725514.247, "dur": 3.852, + "args": { + "External id": 1411756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725514.835, "dur": 3.183, + "args": { + "External id": 1411757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725522.890, "dur": 5.587, + "args": { + "External id": 1411758,"Record function id": 0, "Ev Idx": 4269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725524.570, "dur": 3.385, + "args": { + "External id": 1411759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725525.690, "dur": 1.783, + "args": { + "External id": 1411760,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725526.273, "dur": 1.066, + "args": { + "External id": 1411761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725532.104, "dur": 7.202, + "args": { + "External id": 1411762,"Record function id": 0, "Ev Idx": 4273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725533.804, "dur": 4.968, + "args": { + "External id": 1411763,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725534.404, "dur": 3.871, + "args": { + "External id": 1411764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725537.488, "dur": 0.660, + "args": { + "External id": 1411765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725543.121, "dur": 4.669, + "args": { + "External id": 1411766,"Record function id": 0, "Ev Idx": 4277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725544.599, "dur": 2.684, + "args": { + "External id": 1411767,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725545.410, "dur": 1.415, + "args": { + "External id": 1411768,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725545.950, "dur": 0.754, + "args": { + "External id": 1411769,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725551.658, "dur": 4.355, + "args": { + "External id": 1411770,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725552.894, "dur": 2.632, + "args": { + "External id": 1411771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725553.723, "dur": 1.308, + "args": { + "External id": 1411772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725554.199, "dur": 0.746, + "args": { + "External id": 1411773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725559.792, "dur": 4.407, + "args": { + "External id": 1411774,"Record function id": 0, "Ev Idx": 4285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725561.282, "dur": 2.411, + "args": { + "External id": 1411775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725561.912, "dur": 1.298, + "args": { + "External id": 1411776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725562.368, "dur": 0.720, + "args": { + "External id": 1411777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725568.008, "dur": 7.137, + "args": { + "External id": 1411778,"Record function id": 0, "Ev Idx": 4289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532725569.392, "dur": 5.192, + "args": { + "External id": 1411779,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725570.232, "dur": 3.901, + "args": { + "External id": 1411780,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532725573.121, "dur": 0.897, + "args": { + "External id": 1411781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532725580.222, "dur": 63528.650, + "args": { + "External id": 1411782,"Record function id": 0, "Sequence number": 15108861, "Fwd thread id": 1, "Ev Idx": 4293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532725582.618, "dur": 63462.045, + "args": { + "External id": 1411783,"Sequence number": 15108861, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4294 + } + }, + { + "ph": "f", "id": 205, "pid": 2338710, "tid": 2379450, "ts": 6410532725582.618, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410532725617.416, "dur": 46.008, + "args": { + "External id": 1411784,"Record function id": 0, "Ev Idx": 4295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410532725673.698, "dur": 75.400, + "args": { + "External id": 1411785,"Record function id": 0, "Ev Idx": 4296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410532725761.461, "dur": 63274.357, + "args": { + "External id": 1411786,"Record function id": 0, "Ev Idx": 4297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532725897.539, "dur": 12.094, + "args": { + "External id": 1411787,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532725925.292, "dur": 10.536, + "args": { + "External id": 1411788,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532725957.017, "dur": 62059.603, + "args": { + "External id": 1411789,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532725978.728, "dur": 62021.891, + "args": { + "External id": 1411790,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532726167.284, "dur": 279.286, + "args": { + "External id": 1411791,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532726475.539, "dur": 61465.833, + "args": { + "External id": 1411792,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532726675.017, "dur": 61265.067, + "args": { + "External id": 1411793,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532726682.604, "dur": 20.063, + "args": { + "External id": 1411794,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532726707.960, "dur": 61226.777, + "args": { + "External id": 1411795,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532788197.991, "dur": 15.880, + "args": { + "External id": 1411796,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532788202.432, "dur": 10.783, + "args": { + "External id": 1411797,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532788251.013, "dur": 440.381, + "args": { + "External id": 1411798,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532788290.426, "dur": 394.322, + "args": { + "External id": 1411799,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4310, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532788306.063, "dur": 372.458, + "args": { + "External id": 1411800,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532788719.995, "dur": 2.764, + "args": { + "External id": 1411801,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4312, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788796.678, "dur": 7.976, + "args": { + "External id": 1411802,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788856.728, "dur": 1.721, + "args": { + "External id": 1411803,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788876.705, "dur": 4.193, + "args": { + "External id": 1411804,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788893.924, "dur": 1.186, + "args": { + "External id": 1411805,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788907.159, "dur": 0.997, + "args": { + "External id": 1411806,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788919.692, "dur": 1.176, + "args": { + "External id": 1411807,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788935.054, "dur": 3.521, + "args": { + "External id": 1411808,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788949.914, "dur": 2.315, + "args": { + "External id": 1411809,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532788962.905, "dur": 0.936, + "args": { + "External id": 1411810,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532789129.879, "dur": 3495.469, + "args": { + "External id": 1411811,"Record function id": 0, "Ev Idx": 4322 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410532789157.712, "dur": 1324.903, + "args": { + "External id": 1411812,"Record function id": 0, "Ev Idx": 4323 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410532789176.727, "dur": 421.206, + "args": { + "External id": 1411813,"Record function id": 0, "Ev Idx": 4324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789290.888, "dur": 5.892, + "args": { + "External id": 1411814,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789300.989, "dur": 1.060, + "args": { + "External id": 1411815,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789304.167, "dur": 3.131, + "args": { + "External id": 1411816,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789309.400, "dur": 0.972, + "args": { + "External id": 1411817,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789314.478, "dur": 0.904, + "args": { + "External id": 1411818,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789317.116, "dur": 0.891, + "args": { + "External id": 1411819,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789320.173, "dur": 2.200, + "args": { + "External id": 1411820,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789324.244, "dur": 0.880, + "args": { + "External id": 1411821,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789328.833, "dur": 1.099, + "args": { + "External id": 1411822,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532789331.806, "dur": 0.648, + "args": { + "External id": 1411823,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532789353.541, "dur": 201.368, + "args": { + "External id": 1411824,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532789373.000, "dur": 175.837, + "args": { + "External id": 1411825,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532789393.832, "dur": 34.051, + "args": { + "External id": 1411826,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532789433.969, "dur": 80.885, + "args": { + "External id": 1411827,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532789437.000, "dur": 77.269, + "args": { + "External id": 1411828,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789442.746, "dur": 6.959, + "args": { + "External id": 1411829,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532789453.757, "dur": 59.752, + "args": { + "External id": 1411830,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.7", "pid": 2338710, "tid": 2379450, + "ts": 6410532789711.629, "dur": 761.792, + "args": { + "External id": 1411831,"Record function id": 0, "Ev Idx": 4342 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410532789733.078, "dur": 724.193, + "args": { + "External id": 1411832,"Record function id": 0, "Ev Idx": 4343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532789806.396, "dur": 6.171, + "args": { + "External id": 1411833,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532789830.095, "dur": 39.997, + "args": { + "External id": 1411834,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789836.255, "dur": 3.848, + "args": { + "External id": 1411835,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789842.339, "dur": 0.565, + "args": { + "External id": 1411836,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789844.768, "dur": 0.533, + "args": { + "External id": 1411837,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789848.500, "dur": 0.838, + "args": { + "External id": 1411838,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789851.260, "dur": 0.887, + "args": { + "External id": 1411839,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789854.090, "dur": 2.863, + "args": { + "External id": 1411840,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789859.275, "dur": 0.374, + "args": { + "External id": 1411841,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789861.141, "dur": 0.552, + "args": { + "External id": 1411842,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789863.783, "dur": 1.442, + "args": { + "External id": 1411843,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532789882.184, "dur": 50.469, + "args": { + "External id": 1411844,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532789968.278, "dur": 184.582, + "args": { + "External id": 1411845,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532789980.610, "dur": 4.546, + "args": { + "External id": 1411846,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532789991.251, "dur": 11.084, + "args": { + "External id": 1411847,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532789995.738, "dur": 6.117, + "args": { + "External id": 1411848,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532789999.806, "dur": 0.575, + "args": { + "External id": 1411849,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532790010.843, "dur": 34.873, + "args": { + "External id": 1411850,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790013.595, "dur": 0.739, + "args": { + "External id": 1411851,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790016.383, "dur": 0.557, + "args": { + "External id": 1411852,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790022.300, "dur": 4.036, + "args": { + "External id": 1411853,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790028.142, "dur": 0.281, + "args": { + "External id": 1411854,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790030.081, "dur": 0.290, + "args": { + "External id": 1411855,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790033.444, "dur": 0.692, + "args": { + "External id": 1411856,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790035.496, "dur": 0.410, + "args": { + "External id": 1411857,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790037.674, "dur": 0.474, + "args": { + "External id": 1411858,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532790041.069, "dur": 0.296, + "args": { + "External id": 1411859,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532790100.380, "dur": 41.063, + "args": { + "External id": 1411860,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532790210.612, "dur": 142.553, + "args": { + "External id": 1411861,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532790247.882, "dur": 101.035, + "args": { + "External id": 1411862,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4373, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532790258.827, "dur": 85.603, + "args": { + "External id": 1411863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532790377.277, "dur": 2.136, + "args": { + "External id": 1411864,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4375, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532790492.898, "dur": 2104.964, + "args": { + "External id": 1411865,"Sequence number": 15108860, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4376 + } + }, + { + "ph": "f", "id": 206, "pid": 2338710, "tid": 2379450, "ts": 6410532790492.898, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532790628.431, "dur": 126.032, + "args": { + "External id": 1411866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532790812.273, "dur": 47.948, + "args": { + "External id": 1411867,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532790881.231, "dur": 58.929, + "args": { + "External id": 1411868,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532790955.838, "dur": 36.988, + "args": { + "External id": 1411869,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532790999.820, "dur": 37.102, + "args": { + "External id": 1411870,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532791044.165, "dur": 76.209, + "args": { + "External id": 1411871,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532791133.170, "dur": 37.113, + "args": { + "External id": 1411872,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532791208.207, "dur": 29.467, + "args": { + "External id": 1411873,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532791260.299, "dur": 38.987, + "args": { + "External id": 1411874,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532791326.715, "dur": 26.330, + "args": { + "External id": 1411875,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532791368.251, "dur": 16.796, + "args": { + "External id": 1411876,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532791393.521, "dur": 62.868, + "args": { + "External id": 1411877,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532791462.546, "dur": 41.429, + "args": { + "External id": 1411878,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532791541.986, "dur": 321.534, + "args": { + "External id": 1411879,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532791634.216, "dur": 7.132, + "args": { + "External id": 1411880,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532791643.828, "dur": 2.955, + "args": { + "External id": 1411881,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532791648.348, "dur": 1.990, + "args": { + "External id": 1411882,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532791651.646, "dur": 3.024, + "args": { + "External id": 1411883,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532791708.667, "dur": 8.347, + "args": { + "External id": 1411884,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532791713.392, "dur": 3.433, + "args": { + "External id": 1411885,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532791719.122, "dur": 55.982, + "args": { + "External id": 1411886,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532791725.025, "dur": 3.585, + "args": { + "External id": 1411887,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532791780.273, "dur": 2.225, + "args": { + "External id": 1411888,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532791781.540, "dur": 0.873, + "args": { + "External id": 1411889,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532791783.947, "dur": 18.811, + "args": { + "External id": 1411890,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532791787.004, "dur": 0.721, + "args": { + "External id": 1411891,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532791913.431, "dur": 34.086, + "args": { + "External id": 1411892,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532791970.420, "dur": 18.003, + "args": { + "External id": 1411893,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532791998.165, "dur": 52.682, + "args": { + "External id": 1411894,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532792098.521, "dur": 52.941, + "args": { + "External id": 1411895,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532792166.123, "dur": 27.031, + "args": { + "External id": 1411896,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532792200.094, "dur": 35.698, + "args": { + "External id": 1411897,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532792244.392, "dur": 33.129, + "args": { + "External id": 1411898,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532792285.162, "dur": 33.263, + "args": { + "External id": 1411899,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532792345.945, "dur": 29.625, + "args": { + "External id": 1411900,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532792394.287, "dur": 48.356, + "args": { + "External id": 1411901,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532792465.350, "dur": 22.398, + "args": { + "External id": 1411902,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532792512.418, "dur": 18.400, + "args": { + "External id": 1411903,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532792545.735, "dur": 18.106, + "args": { + "External id": 1411904,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792651.004, "dur": 17.237, + "args": { + "External id": 1411905,"Record function id": 0, "Ev Idx": 4416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792654.570, "dur": 12.492, + "args": { + "External id": 1411906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792659.530, "dur": 6.372, + "args": { + "External id": 1411907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792661.221, "dur": 4.574, + "args": { + "External id": 1411908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792672.840, "dur": 6.115, + "args": { + "External id": 1411909,"Record function id": 0, "Ev Idx": 4420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792674.794, "dur": 3.673, + "args": { + "External id": 1411910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792675.725, "dur": 1.934, + "args": { + "External id": 1411911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792676.488, "dur": 1.093, + "args": { + "External id": 1411912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792682.984, "dur": 8.205, + "args": { + "External id": 1411913,"Record function id": 0, "Ev Idx": 4424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792684.635, "dur": 6.022, + "args": { + "External id": 1411914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792685.488, "dur": 4.660, + "args": { + "External id": 1411915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792686.255, "dur": 3.790, + "args": { + "External id": 1411916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792694.992, "dur": 4.748, + "args": { + "External id": 1411917,"Record function id": 0, "Ev Idx": 4428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792696.639, "dur": 2.622, + "args": { + "External id": 1411918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792697.301, "dur": 1.444, + "args": { + "External id": 1411919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792697.896, "dur": 0.775, + "args": { + "External id": 1411920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792703.428, "dur": 4.582, + "args": { + "External id": 1411921,"Record function id": 0, "Ev Idx": 4432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792704.996, "dur": 2.507, + "args": { + "External id": 1411922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792705.712, "dur": 1.278, + "args": { + "External id": 1411923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792706.145, "dur": 0.761, + "args": { + "External id": 1411924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792711.825, "dur": 5.113, + "args": { + "External id": 1411925,"Record function id": 0, "Ev Idx": 4436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792713.415, "dur": 3.033, + "args": { + "External id": 1411926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792714.595, "dur": 1.333, + "args": { + "External id": 1411927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792715.073, "dur": 0.780, + "args": { + "External id": 1411928,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792720.756, "dur": 10.381, + "args": { + "External id": 1411929,"Record function id": 0, "Ev Idx": 4440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792722.062, "dur": 8.598, + "args": { + "External id": 1411930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792722.928, "dur": 7.224, + "args": { + "External id": 1411931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792729.415, "dur": 0.630, + "args": { + "External id": 1411932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792734.962, "dur": 4.646, + "args": { + "External id": 1411933,"Record function id": 0, "Ev Idx": 4444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792736.629, "dur": 2.495, + "args": { + "External id": 1411934,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792737.350, "dur": 1.291, + "args": { + "External id": 1411935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792737.773, "dur": 0.772, + "args": { + "External id": 1411936,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792743.240, "dur": 4.261, + "args": { + "External id": 1411937,"Record function id": 0, "Ev Idx": 4448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532792744.479, "dur": 2.532, + "args": { + "External id": 1411938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792745.404, "dur": 1.081, + "args": { + "External id": 1411939,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532792745.784, "dur": 0.615, + "args": { + "External id": 1411940,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532792752.448, "dur": 64110.446, + "args": { + "External id": 1411941,"Record function id": 0, "Sequence number": 15108859, "Fwd thread id": 1, "Ev Idx": 4452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532792754.242, "dur": 64097.610, + "args": { + "External id": 1411942,"Sequence number": 15108859, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4453 + } + }, + { + "ph": "f", "id": 207, "pid": 2338710, "tid": 2379450, "ts": 6410532792754.242, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410532792792.217, "dur": 48.744, + "args": { + "External id": 1411943,"Record function id": 0, "Ev Idx": 4454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410532792853.371, "dur": 98.840, + "args": { + "External id": 1411944,"Record function id": 0, "Ev Idx": 4455 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410532792963.437, "dur": 63879.544, + "args": { + "External id": 1411945,"Record function id": 0, "Ev Idx": 4456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532793139.795, "dur": 14.849, + "args": { + "External id": 1411946,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532793173.277, "dur": 10.756, + "args": { + "External id": 1411947,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532793211.013, "dur": 62705.913, + "args": { + "External id": 1411948,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532793231.815, "dur": 62668.650, + "args": { + "External id": 1411949,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532793718.758, "dur": 33.326, + "args": { + "External id": 1411950,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532793782.989, "dur": 62056.779, + "args": { + "External id": 1411951,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532793787.110, "dur": 62050.915, + "args": { + "External id": 1411952,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532793795.670, "dur": 18.099, + "args": { + "External id": 1411953,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532793816.948, "dur": 62013.844, + "args": { + "External id": 1411954,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532856095.386, "dur": 21.898, + "args": { + "External id": 1411955,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532856102.271, "dur": 14.111, + "args": { + "External id": 1411956,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532856159.220, "dur": 334.008, + "args": { + "External id": 1411957,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532856198.414, "dur": 288.755, + "args": { + "External id": 1411958,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4469, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532856214.264, "dur": 263.162, + "args": { + "External id": 1411959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532856521.349, "dur": 2.774, + "args": { + "External id": 1411960,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4471, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856600.678, "dur": 7.751, + "args": { + "External id": 1411961,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856660.461, "dur": 1.702, + "args": { + "External id": 1411962,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856680.814, "dur": 4.019, + "args": { + "External id": 1411963,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856699.077, "dur": 0.851, + "args": { + "External id": 1411964,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856714.840, "dur": 0.800, + "args": { + "External id": 1411965,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856728.174, "dur": 1.053, + "args": { + "External id": 1411966,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856741.258, "dur": 3.686, + "args": { + "External id": 1411967,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856757.250, "dur": 2.350, + "args": { + "External id": 1411968,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532856771.156, "dur": 0.800, + "args": { + "External id": 1411969,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532856878.556, "dur": 4299.557, + "args": { + "External id": 1411970,"Record function id": 0, "Ev Idx": 4481 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410532856904.699, "dur": 1421.102, + "args": { + "External id": 1411971,"Record function id": 0, "Ev Idx": 4482 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410532856922.329, "dur": 464.864, + "args": { + "External id": 1411972,"Record function id": 0, "Ev Idx": 4483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857027.734, "dur": 4.918, + "args": { + "External id": 1411973,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857036.679, "dur": 1.275, + "args": { + "External id": 1411974,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857040.021, "dur": 3.436, + "args": { + "External id": 1411975,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857045.633, "dur": 0.852, + "args": { + "External id": 1411976,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857048.145, "dur": 1.133, + "args": { + "External id": 1411977,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857051.172, "dur": 0.875, + "args": { + "External id": 1411978,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857054.619, "dur": 57.339, + "args": { + "External id": 1411979,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857121.412, "dur": 1.980, + "args": { + "External id": 1411980,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857126.248, "dur": 1.456, + "args": { + "External id": 1411981,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532857130.426, "dur": 0.947, + "args": { + "External id": 1411982,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532857157.273, "dur": 188.181, + "args": { + "External id": 1411983,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532857177.061, "dur": 162.312, + "args": { + "External id": 1411984,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532857199.441, "dur": 20.533, + "args": { + "External id": 1411985,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532857226.125, "dur": 78.690, + "args": { + "External id": 1411986,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532857229.169, "dur": 75.195, + "args": { + "External id": 1411987,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857234.193, "dur": 7.311, + "args": { + "External id": 1411988,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532857243.347, "dur": 60.480, + "args": { + "External id": 1411989,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4500 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.6", "pid": 2338710, "tid": 2379450, + "ts": 6410532857526.629, "dur": 789.600, + "args": { + "External id": 1411990,"Record function id": 0, "Ev Idx": 4501 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410532857550.236, "dur": 749.926, + "args": { + "External id": 1411991,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532857629.500, "dur": 7.050, + "args": { + "External id": 1411992,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532857654.977, "dur": 39.096, + "args": { + "External id": 1411993,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857661.077, "dur": 3.372, + "args": { + "External id": 1411994,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857666.713, "dur": 0.409, + "args": { + "External id": 1411995,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857668.664, "dur": 0.443, + "args": { + "External id": 1411996,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857672.197, "dur": 0.405, + "args": { + "External id": 1411997,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857674.615, "dur": 0.417, + "args": { + "External id": 1411998,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857676.929, "dur": 2.587, + "args": { + "External id": 1411999,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857682.480, "dur": 0.536, + "args": { + "External id": 1412000,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857684.589, "dur": 0.329, + "args": { + "External id": 1412001,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857686.422, "dur": 1.722, + "args": { + "External id": 1412002,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532857705.960, "dur": 52.232, + "args": { + "External id": 1412003,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532857795.260, "dur": 133.352, + "args": { + "External id": 1412004,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532857810.967, "dur": 4.680, + "args": { + "External id": 1412005,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532857821.597, "dur": 11.585, + "args": { + "External id": 1412006,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532857826.331, "dur": 6.382, + "args": { + "External id": 1412007,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857830.617, "dur": 0.532, + "args": { + "External id": 1412008,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532857840.813, "dur": 33.664, + "args": { + "External id": 1412009,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857843.332, "dur": 0.585, + "args": { + "External id": 1412010,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857845.938, "dur": 0.523, + "args": { + "External id": 1412011,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857847.893, "dur": 3.818, + "args": { + "External id": 1412012,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857853.797, "dur": 0.599, + "args": { + "External id": 1412013,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857855.938, "dur": 0.463, + "args": { + "External id": 1412014,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857859.410, "dur": 0.357, + "args": { + "External id": 1412015,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857860.916, "dur": 0.357, + "args": { + "External id": 1412016,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857862.872, "dur": 0.366, + "args": { + "External id": 1412017,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532857869.207, "dur": 0.399, + "args": { + "External id": 1412018,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532857886.015, "dur": 34.136, + "args": { + "External id": 1412019,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532857981.395, "dur": 216.048, + "args": { + "External id": 1412020,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532858015.664, "dur": 173.278, + "args": { + "External id": 1412021,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4532, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532858026.363, "dur": 156.422, + "args": { + "External id": 1412022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532858224.392, "dur": 2.485, + "args": { + "External id": 1412023,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4534, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532858333.686, "dur": 2816.876, + "args": { + "External id": 1412024,"Sequence number": 15108858, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4535 + } + }, + { + "ph": "f", "id": 208, "pid": 2338710, "tid": 2379450, "ts": 6410532858333.686, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532858490.724, "dur": 128.392, + "args": { + "External id": 1412025,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532858669.296, "dur": 48.705, + "args": { + "External id": 1412026,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532858751.427, "dur": 60.628, + "args": { + "External id": 1412027,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532858826.962, "dur": 36.157, + "args": { + "External id": 1412028,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532858870.531, "dur": 37.698, + "args": { + "External id": 1412029,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532858915.535, "dur": 30.656, + "args": { + "External id": 1412030,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532858954.018, "dur": 32.130, + "args": { + "External id": 1412031,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532859020.723, "dur": 27.889, + "args": { + "External id": 1412032,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532859130.513, "dur": 39.317, + "args": { + "External id": 1412033,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532859203.247, "dur": 23.922, + "args": { + "External id": 1412034,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532859243.372, "dur": 18.652, + "args": { + "External id": 1412035,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532859272.781, "dur": 53.243, + "args": { + "External id": 1412036,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532859330.405, "dur": 36.253, + "args": { + "External id": 1412037,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532859411.885, "dur": 910.358, + "args": { + "External id": 1412038,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532859572.394, "dur": 15.738, + "args": { + "External id": 1412039,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532859593.364, "dur": 4.493, + "args": { + "External id": 1412040,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532859600.146, "dur": 3.135, + "args": { + "External id": 1412041,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532859605.322, "dur": 4.937, + "args": { + "External id": 1412042,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532859702.739, "dur": 12.234, + "args": { + "External id": 1412043,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532859710.686, "dur": 3.956, + "args": { + "External id": 1412044,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532859720.498, "dur": 50.978, + "args": { + "External id": 1412045,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532859729.222, "dur": 7.689, + "args": { + "External id": 1412046,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532859773.799, "dur": 2.533, + "args": { + "External id": 1412047,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532859775.225, "dur": 0.948, + "args": { + "External id": 1412048,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532859777.902, "dur": 225.594, + "args": { + "External id": 1412049,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532859783.457, "dur": 0.701, + "args": { + "External id": 1412050,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532860393.536, "dur": 60.766, + "args": { + "External id": 1412051,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532860484.822, "dur": 21.352, + "args": { + "External id": 1412052,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532860519.225, "dur": 81.919, + "args": { + "External id": 1412053,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532860609.814, "dur": 50.547, + "args": { + "External id": 1412054,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532860673.793, "dur": 24.295, + "args": { + "External id": 1412055,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532860704.232, "dur": 34.948, + "args": { + "External id": 1412056,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532860747.666, "dur": 31.591, + "args": { + "External id": 1412057,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532860787.872, "dur": 34.123, + "args": { + "External id": 1412058,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532860849.536, "dur": 30.228, + "args": { + "External id": 1412059,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532860902.142, "dur": 29.751, + "args": { + "External id": 1412060,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532860952.140, "dur": 20.909, + "args": { + "External id": 1412061,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532860994.889, "dur": 18.598, + "args": { + "External id": 1412062,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532861031.670, "dur": 22.729, + "args": { + "External id": 1412063,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861205.373, "dur": 17.302, + "args": { + "External id": 1412064,"Record function id": 0, "Ev Idx": 4575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861209.372, "dur": 12.234, + "args": { + "External id": 1412065,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861214.248, "dur": 6.276, + "args": { + "External id": 1412066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861215.895, "dur": 4.495, + "args": { + "External id": 1412067,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861227.322, "dur": 5.876, + "args": { + "External id": 1412068,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861229.214, "dur": 3.430, + "args": { + "External id": 1412069,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861230.119, "dur": 1.770, + "args": { + "External id": 1412070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861230.861, "dur": 0.877, + "args": { + "External id": 1412071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861237.129, "dur": 7.739, + "args": { + "External id": 1412072,"Record function id": 0, "Ev Idx": 4583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861238.674, "dur": 5.672, + "args": { + "External id": 1412073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861239.682, "dur": 4.179, + "args": { + "External id": 1412074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861240.425, "dur": 3.331, + "args": { + "External id": 1412075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861248.562, "dur": 4.696, + "args": { + "External id": 1412076,"Record function id": 0, "Ev Idx": 4587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861250.096, "dur": 2.720, + "args": { + "External id": 1412077,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861250.910, "dur": 1.412, + "args": { + "External id": 1412078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861251.295, "dur": 0.893, + "args": { + "External id": 1412079,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861256.855, "dur": 4.299, + "args": { + "External id": 1412080,"Record function id": 0, "Ev Idx": 4591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861258.623, "dur": 2.031, + "args": { + "External id": 1412081,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861259.144, "dur": 1.054, + "args": { + "External id": 1412082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861259.454, "dur": 0.657, + "args": { + "External id": 1412083,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861264.654, "dur": 4.915, + "args": { + "External id": 1412084,"Record function id": 0, "Ev Idx": 4595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861265.996, "dur": 3.120, + "args": { + "External id": 1412085,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861266.812, "dur": 1.836, + "args": { + "External id": 1412086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861267.703, "dur": 0.819, + "args": { + "External id": 1412087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861283.038, "dur": 11.105, + "args": { + "External id": 1412088,"Record function id": 0, "Ev Idx": 4599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861287.031, "dur": 6.191, + "args": { + "External id": 1412089,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861288.469, "dur": 2.660, + "args": { + "External id": 1412090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861289.038, "dur": 1.844, + "args": { + "External id": 1412091,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861298.789, "dur": 7.781, + "args": { + "External id": 1412092,"Record function id": 0, "Ev Idx": 4603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861300.351, "dur": 5.758, + "args": { + "External id": 1412093,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861301.281, "dur": 3.998, + "args": { + "External id": 1412094,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861304.346, "dur": 0.847, + "args": { + "External id": 1412095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861310.265, "dur": 41.421, + "args": { + "External id": 1412096,"Record function id": 0, "Ev Idx": 4607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532861348.303, "dur": 2.909, + "args": { + "External id": 1412097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861349.357, "dur": 1.291, + "args": { + "External id": 1412098,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532861349.789, "dur": 0.714, + "args": { + "External id": 1412099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532861357.038, "dur": 60029.896, + "args": { + "External id": 1412100,"Record function id": 0, "Sequence number": 15108857, "Fwd thread id": 1, "Ev Idx": 4611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532861359.382, "dur": 60017.641, + "args": { + "External id": 1412101,"Sequence number": 15108857, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4612 + } + }, + { + "ph": "f", "id": 209, "pid": 2338710, "tid": 2379450, "ts": 6410532861359.382, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410532861403.181, "dur": 70.068, + "args": { + "External id": 1412102,"Record function id": 0, "Ev Idx": 4613 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410532861484.618, "dur": 81.205, + "args": { + "External id": 1412103,"Record function id": 0, "Ev Idx": 4614 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410532861573.033, "dur": 59794.328, + "args": { + "External id": 1412104,"Record function id": 0, "Ev Idx": 4615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532861684.681, "dur": 9.820, + "args": { + "External id": 1412105,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532861706.343, "dur": 8.800, + "args": { + "External id": 1412106,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532861731.883, "dur": 58555.786, + "args": { + "External id": 1412107,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532861753.232, "dur": 58518.601, + "args": { + "External id": 1412108,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532861876.812, "dur": 30.179, + "args": { + "External id": 1412109,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532861936.327, "dur": 58276.799, + "args": { + "External id": 1412110,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532861940.485, "dur": 58271.288, + "args": { + "External id": 1412111,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532861947.287, "dur": 16.183, + "args": { + "External id": 1412112,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532861966.600, "dur": 58239.009, + "args": { + "External id": 1412113,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532920428.326, "dur": 17.363, + "args": { + "External id": 1412114,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532920433.479, "dur": 11.644, + "args": { + "External id": 1412115,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532920486.526, "dur": 484.579, + "args": { + "External id": 1412116,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532920525.684, "dur": 439.776, + "args": { + "External id": 1412117,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4628, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532920541.944, "dur": 417.189, + "args": { + "External id": 1412118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532920997.299, "dur": 2.592, + "args": { + "External id": 1412119,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4630, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921125.553, "dur": 8.325, + "args": { + "External id": 1412120,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921187.343, "dur": 1.458, + "args": { + "External id": 1412121,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921206.737, "dur": 4.071, + "args": { + "External id": 1412122,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921224.058, "dur": 0.843, + "args": { + "External id": 1412123,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921237.997, "dur": 1.035, + "args": { + "External id": 1412124,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921251.248, "dur": 0.855, + "args": { + "External id": 1412125,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921263.969, "dur": 3.933, + "args": { + "External id": 1412126,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921280.198, "dur": 2.301, + "args": { + "External id": 1412127,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921293.315, "dur": 0.751, + "args": { + "External id": 1412128,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532921405.619, "dur": 3537.652, + "args": { + "External id": 1412129,"Record function id": 0, "Ev Idx": 4640 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410532921449.289, "dur": 1314.363, + "args": { + "External id": 1412130,"Record function id": 0, "Ev Idx": 4641 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410532921466.272, "dur": 393.851, + "args": { + "External id": 1412131,"Record function id": 0, "Ev Idx": 4642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921570.300, "dur": 5.356, + "args": { + "External id": 1412132,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921579.534, "dur": 1.186, + "args": { + "External id": 1412133,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921582.685, "dur": 3.426, + "args": { + "External id": 1412134,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921590.743, "dur": 0.998, + "args": { + "External id": 1412135,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921593.813, "dur": 0.761, + "args": { + "External id": 1412136,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921596.429, "dur": 0.904, + "args": { + "External id": 1412137,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921599.210, "dur": 2.084, + "args": { + "External id": 1412138,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921605.301, "dur": 0.881, + "args": { + "External id": 1412139,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921607.747, "dur": 0.971, + "args": { + "External id": 1412140,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532921610.950, "dur": 1.028, + "args": { + "External id": 1412141,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532921634.027, "dur": 189.916, + "args": { + "External id": 1412142,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532921653.093, "dur": 164.928, + "args": { + "External id": 1412143,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532921674.675, "dur": 19.477, + "args": { + "External id": 1412144,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532921700.734, "dur": 83.423, + "args": { + "External id": 1412145,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532921703.728, "dur": 79.971, + "args": { + "External id": 1412146,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532921708.300, "dur": 6.489, + "args": { + "External id": 1412147,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532921716.965, "dur": 66.001, + "args": { + "External id": 1412148,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4659 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.5", "pid": 2338710, "tid": 2379450, + "ts": 6410532921964.324, "dur": 789.721, + "args": { + "External id": 1412149,"Record function id": 0, "Ev Idx": 4660 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410532921984.528, "dur": 754.991, + "args": { + "External id": 1412150,"Record function id": 0, "Ev Idx": 4661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532922125.249, "dur": 9.053, + "args": { + "External id": 1412151,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532922153.655, "dur": 37.775, + "args": { + "External id": 1412152,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922159.917, "dur": 3.473, + "args": { + "External id": 1412153,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922165.501, "dur": 0.512, + "args": { + "External id": 1412154,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922167.808, "dur": 0.455, + "args": { + "External id": 1412155,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922171.188, "dur": 0.511, + "args": { + "External id": 1412156,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922173.628, "dur": 0.457, + "args": { + "External id": 1412157,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922175.655, "dur": 2.863, + "args": { + "External id": 1412158,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922180.516, "dur": 0.277, + "args": { + "External id": 1412159,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922182.614, "dur": 0.428, + "args": { + "External id": 1412160,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922184.635, "dur": 1.288, + "args": { + "External id": 1412161,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532922204.547, "dur": 56.542, + "args": { + "External id": 1412162,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532922301.934, "dur": 151.523, + "args": { + "External id": 1412163,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532922314.112, "dur": 4.259, + "args": { + "External id": 1412164,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532922324.485, "dur": 11.276, + "args": { + "External id": 1412165,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532922329.326, "dur": 5.968, + "args": { + "External id": 1412166,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922333.149, "dur": 0.900, + "args": { + "External id": 1412167,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532922343.613, "dur": 28.288, + "args": { + "External id": 1412168,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922346.274, "dur": 0.339, + "args": { + "External id": 1412169,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922348.360, "dur": 0.537, + "args": { + "External id": 1412170,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922350.652, "dur": 2.843, + "args": { + "External id": 1412171,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922355.019, "dur": 0.603, + "args": { + "External id": 1412172,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922357.416, "dur": 0.414, + "args": { + "External id": 1412173,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922360.619, "dur": 0.450, + "args": { + "External id": 1412174,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922362.609, "dur": 0.299, + "args": { + "External id": 1412175,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922364.608, "dur": 0.577, + "args": { + "External id": 1412176,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532922367.588, "dur": 0.479, + "args": { + "External id": 1412177,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532922386.434, "dur": 55.729, + "args": { + "External id": 1412178,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532922512.833, "dur": 140.661, + "args": { + "External id": 1412179,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532922548.379, "dur": 101.221, + "args": { + "External id": 1412180,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4691, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532922559.674, "dur": 85.036, + "args": { + "External id": 1412181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532922675.536, "dur": 2.066, + "args": { + "External id": 1412182,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4693, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532922772.177, "dur": 2147.408, + "args": { + "External id": 1412183,"Sequence number": 15108856, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4694 + } + }, + { + "ph": "f", "id": 210, "pid": 2338710, "tid": 2379450, "ts": 6410532922772.177, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532922902.602, "dur": 120.815, + "args": { + "External id": 1412184,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532923126.419, "dur": 52.886, + "args": { + "External id": 1412185,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532923204.271, "dur": 67.779, + "args": { + "External id": 1412186,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532923285.714, "dur": 36.852, + "args": { + "External id": 1412187,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532923346.577, "dur": 36.994, + "args": { + "External id": 1412188,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532923391.767, "dur": 48.337, + "args": { + "External id": 1412189,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532923453.349, "dur": 40.146, + "args": { + "External id": 1412190,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532923532.889, "dur": 29.129, + "args": { + "External id": 1412191,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532923588.858, "dur": 32.886, + "args": { + "External id": 1412192,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532923650.326, "dur": 24.998, + "args": { + "External id": 1412193,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532923690.616, "dur": 16.225, + "args": { + "External id": 1412194,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532923718.569, "dur": 41.810, + "args": { + "External id": 1412195,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532923764.837, "dur": 37.279, + "args": { + "External id": 1412196,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532923835.245, "dur": 377.864, + "args": { + "External id": 1412197,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532923943.268, "dur": 8.957, + "args": { + "External id": 1412198,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532923955.218, "dur": 3.040, + "args": { + "External id": 1412199,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532923959.991, "dur": 3.602, + "args": { + "External id": 1412200,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532923964.962, "dur": 3.243, + "args": { + "External id": 1412201,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532924022.659, "dur": 5.902, + "args": { + "External id": 1412202,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532924024.984, "dur": 3.404, + "args": { + "External id": 1412203,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532924033.023, "dur": 92.941, + "args": { + "External id": 1412204,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532924039.345, "dur": 4.139, + "args": { + "External id": 1412205,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532924129.488, "dur": 2.705, + "args": { + "External id": 1412206,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532924130.942, "dur": 1.137, + "args": { + "External id": 1412207,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532924134.029, "dur": 21.490, + "args": { + "External id": 1412208,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532924138.772, "dur": 1.003, + "args": { + "External id": 1412209,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532924260.372, "dur": 34.161, + "args": { + "External id": 1412210,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532924322.586, "dur": 19.728, + "args": { + "External id": 1412211,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532924352.032, "dur": 80.004, + "args": { + "External id": 1412212,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532924443.930, "dur": 53.749, + "args": { + "External id": 1412213,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532924511.874, "dur": 29.179, + "args": { + "External id": 1412214,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532924547.730, "dur": 36.609, + "args": { + "External id": 1412215,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532924592.884, "dur": 31.660, + "args": { + "External id": 1412216,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532924633.810, "dur": 37.078, + "args": { + "External id": 1412217,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532924697.758, "dur": 27.917, + "args": { + "External id": 1412218,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532924746.958, "dur": 28.024, + "args": { + "External id": 1412219,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532924795.131, "dur": 18.097, + "args": { + "External id": 1412220,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532924834.848, "dur": 16.256, + "args": { + "External id": 1412221,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532924867.816, "dur": 16.693, + "args": { + "External id": 1412222,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532924968.789, "dur": 17.103, + "args": { + "External id": 1412223,"Record function id": 0, "Ev Idx": 4734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532924972.476, "dur": 12.393, + "args": { + "External id": 1412224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532924977.326, "dur": 6.417, + "args": { + "External id": 1412225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532924979.115, "dur": 4.519, + "args": { + "External id": 1412226,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532924990.603, "dur": 6.047, + "args": { + "External id": 1412227,"Record function id": 0, "Ev Idx": 4738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532924992.519, "dur": 3.367, + "args": { + "External id": 1412228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532924993.330, "dur": 1.871, + "args": { + "External id": 1412229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532924994.072, "dur": 1.015, + "args": { + "External id": 1412230,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925000.750, "dur": 7.505, + "args": { + "External id": 1412231,"Record function id": 0, "Ev Idx": 4742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925002.111, "dur": 5.565, + "args": { + "External id": 1412232,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925002.927, "dur": 4.102, + "args": { + "External id": 1412233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925003.687, "dur": 3.229, + "args": { + "External id": 1412234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925012.060, "dur": 4.808, + "args": { + "External id": 1412235,"Record function id": 0, "Ev Idx": 4746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925013.694, "dur": 2.671, + "args": { + "External id": 1412236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925014.370, "dur": 1.357, + "args": { + "External id": 1412237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925014.702, "dur": 0.912, + "args": { + "External id": 1412238,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925020.483, "dur": 4.751, + "args": { + "External id": 1412239,"Record function id": 0, "Ev Idx": 4750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925021.993, "dur": 2.770, + "args": { + "External id": 1412240,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925022.537, "dur": 1.587, + "args": { + "External id": 1412241,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925023.092, "dur": 0.944, + "args": { + "External id": 1412242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925028.994, "dur": 4.826, + "args": { + "External id": 1412243,"Record function id": 0, "Ev Idx": 4754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925030.280, "dur": 3.025, + "args": { + "External id": 1412244,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925031.034, "dur": 1.800, + "args": { + "External id": 1412245,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925031.846, "dur": 0.898, + "args": { + "External id": 1412246,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925037.629, "dur": 5.028, + "args": { + "External id": 1412247,"Record function id": 0, "Ev Idx": 4758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925039.007, "dur": 3.191, + "args": { + "External id": 1412248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925039.864, "dur": 1.730, + "args": { + "External id": 1412249,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925040.660, "dur": 0.809, + "args": { + "External id": 1412250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925046.674, "dur": 7.828, + "args": { + "External id": 1412251,"Record function id": 0, "Ev Idx": 4762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925048.261, "dur": 5.771, + "args": { + "External id": 1412252,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925049.264, "dur": 4.286, + "args": { + "External id": 1412253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925052.775, "dur": 0.685, + "args": { + "External id": 1412254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925105.309, "dur": 8.018, + "args": { + "External id": 1412255,"Record function id": 0, "Ev Idx": 4766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532925107.512, "dur": 5.085, + "args": { + "External id": 1412256,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925108.667, "dur": 2.892, + "args": { + "External id": 1412257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532925109.197, "dur": 2.137, + "args": { + "External id": 1412258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532925118.264, "dur": 70683.986, + "args": { + "External id": 1412259,"Record function id": 0, "Sequence number": 15108855, "Fwd thread id": 1, "Ev Idx": 4770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532925120.583, "dur": 70671.612, + "args": { + "External id": 1412260,"Sequence number": 15108855, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4771 + } + }, + { + "ph": "f", "id": 211, "pid": 2338710, "tid": 2379450, "ts": 6410532925120.583, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410532925160.308, "dur": 50.586, + "args": { + "External id": 1412261,"Record function id": 0, "Ev Idx": 4772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410532925220.930, "dur": 81.985, + "args": { + "External id": 1412262,"Record function id": 0, "Ev Idx": 4773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410532925310.785, "dur": 70472.257, + "args": { + "External id": 1412263,"Record function id": 0, "Ev Idx": 4774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532925437.373, "dur": 9.781, + "args": { + "External id": 1412264,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532925461.169, "dur": 8.546, + "args": { + "External id": 1412265,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532925495.142, "dur": 69261.936, + "args": { + "External id": 1412266,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532925514.655, "dur": 69226.505, + "args": { + "External id": 1412267,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532925613.681, "dur": 20.602, + "args": { + "External id": 1412268,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532925669.977, "dur": 69011.388, + "args": { + "External id": 1412269,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532925673.613, "dur": 69006.339, + "args": { + "External id": 1412270,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532925680.210, "dur": 15.408, + "args": { + "External id": 1412271,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532925698.223, "dur": 68975.186, + "args": { + "External id": 1412272,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532994888.664, "dur": 16.380, + "args": { + "External id": 1412273,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532994893.196, "dur": 11.314, + "args": { + "External id": 1412274,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532994939.632, "dur": 491.445, + "args": { + "External id": 1412275,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532994977.824, "dur": 431.140, + "args": { + "External id": 1412276,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4787, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532994992.767, "dur": 408.406, + "args": { + "External id": 1412277,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532995462.253, "dur": 3.663, + "args": { + "External id": 1412278,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4789, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995540.269, "dur": 8.601, + "args": { + "External id": 1412279,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995601.303, "dur": 1.721, + "args": { + "External id": 1412280,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995621.312, "dur": 3.920, + "args": { + "External id": 1412281,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995638.915, "dur": 1.216, + "args": { + "External id": 1412282,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995654.495, "dur": 0.841, + "args": { + "External id": 1412283,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995667.945, "dur": 0.779, + "args": { + "External id": 1412284,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995681.687, "dur": 3.454, + "args": { + "External id": 1412285,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995696.583, "dur": 2.445, + "args": { + "External id": 1412286,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532995710.392, "dur": 0.922, + "args": { + "External id": 1412287,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532995821.182, "dur": 3501.977, + "args": { + "External id": 1412288,"Record function id": 0, "Ev Idx": 4799 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410532995846.564, "dur": 1351.454, + "args": { + "External id": 1412289,"Record function id": 0, "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410532995864.272, "dur": 465.236, + "args": { + "External id": 1412290,"Record function id": 0, "Ev Idx": 4801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532995972.560, "dur": 4.898, + "args": { + "External id": 1412291,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532995981.455, "dur": 0.808, + "args": { + "External id": 1412292,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532995984.443, "dur": 3.370, + "args": { + "External id": 1412293,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532995989.972, "dur": 0.805, + "args": { + "External id": 1412294,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532995992.515, "dur": 0.751, + "args": { + "External id": 1412295,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532995994.846, "dur": 0.802, + "args": { + "External id": 1412296,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532995997.636, "dur": 1.916, + "args": { + "External id": 1412297,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532996003.817, "dur": 1.120, + "args": { + "External id": 1412298,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532996006.816, "dur": 0.665, + "args": { + "External id": 1412299,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532996009.164, "dur": 0.688, + "args": { + "External id": 1412300,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532996037.116, "dur": 249.596, + "args": { + "External id": 1412301,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532996117.922, "dur": 161.266, + "args": { + "External id": 1412302,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532996143.108, "dur": 18.826, + "args": { + "External id": 1412303,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410532996166.717, "dur": 79.061, + "args": { + "External id": 1412304,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410532996169.752, "dur": 75.626, + "args": { + "External id": 1412305,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996174.487, "dur": 7.461, + "args": { + "External id": 1412306,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532996183.791, "dur": 60.825, + "args": { + "External id": 1412307,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4818 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.4", "pid": 2338710, "tid": 2379450, + "ts": 6410532996458.572, "dur": 729.691, + "args": { + "External id": 1412308,"Record function id": 0, "Ev Idx": 4819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410532996479.636, "dur": 693.778, + "args": { + "External id": 1412309,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532996558.819, "dur": 7.557, + "args": { + "External id": 1412310,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532996584.500, "dur": 37.984, + "args": { + "External id": 1412311,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996590.196, "dur": 3.186, + "args": { + "External id": 1412312,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996595.818, "dur": 0.529, + "args": { + "External id": 1412313,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996598.134, "dur": 0.588, + "args": { + "External id": 1412314,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996602.268, "dur": 0.374, + "args": { + "External id": 1412315,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996603.917, "dur": 0.603, + "args": { + "External id": 1412316,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996606.069, "dur": 2.842, + "args": { + "External id": 1412317,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996611.122, "dur": 0.613, + "args": { + "External id": 1412318,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996613.238, "dur": 0.495, + "args": { + "External id": 1412319,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996615.781, "dur": 1.260, + "args": { + "External id": 1412320,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532996635.290, "dur": 52.874, + "args": { + "External id": 1412321,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410532996725.597, "dur": 126.476, + "args": { + "External id": 1412322,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532996738.157, "dur": 4.403, + "args": { + "External id": 1412323,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410532996748.651, "dur": 11.462, + "args": { + "External id": 1412324,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410532996753.562, "dur": 6.084, + "args": { + "External id": 1412325,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996757.887, "dur": 0.426, + "args": { + "External id": 1412326,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410532996768.130, "dur": 30.072, + "args": { + "External id": 1412327,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996771.008, "dur": 0.448, + "args": { + "External id": 1412328,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996773.547, "dur": 0.666, + "args": { + "External id": 1412329,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996775.653, "dur": 3.594, + "args": { + "External id": 1412330,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996781.091, "dur": 0.263, + "args": { + "External id": 1412331,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996783.151, "dur": 0.406, + "args": { + "External id": 1412332,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996786.522, "dur": 0.306, + "args": { + "External id": 1412333,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996788.454, "dur": 0.426, + "args": { + "External id": 1412334,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996790.428, "dur": 0.361, + "args": { + "External id": 1412335,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532996793.747, "dur": 0.407, + "args": { + "External id": 1412336,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410532996810.276, "dur": 32.945, + "args": { + "External id": 1412337,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410532996904.038, "dur": 139.897, + "args": { + "External id": 1412338,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532996937.357, "dur": 102.476, + "args": { + "External id": 1412339,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4850, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410532996949.559, "dur": 85.616, + "args": { + "External id": 1412340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410532997104.593, "dur": 4.017, + "args": { + "External id": 1412341,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4852, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532997206.809, "dur": 2090.063, + "args": { + "External id": 1412342,"Sequence number": 15108854, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4853 + } + }, + { + "ph": "f", "id": 212, "pid": 2338710, "tid": 2379450, "ts": 6410532997206.809, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532997343.526, "dur": 140.776, + "args": { + "External id": 1412343,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532997560.509, "dur": 47.274, + "args": { + "External id": 1412344,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410532997630.142, "dur": 67.462, + "args": { + "External id": 1412345,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532997716.613, "dur": 36.875, + "args": { + "External id": 1412346,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532997761.353, "dur": 37.668, + "args": { + "External id": 1412347,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532997806.583, "dur": 30.421, + "args": { + "External id": 1412348,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532997847.417, "dur": 32.460, + "args": { + "External id": 1412349,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532997915.302, "dur": 26.160, + "args": { + "External id": 1412350,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410532997964.186, "dur": 32.351, + "args": { + "External id": 1412351,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532998024.960, "dur": 22.811, + "args": { + "External id": 1412352,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532998105.410, "dur": 20.110, + "args": { + "External id": 1412353,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532998137.630, "dur": 50.937, + "args": { + "External id": 1412354,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532998193.515, "dur": 37.768, + "args": { + "External id": 1412355,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410532998267.552, "dur": 335.856, + "args": { + "External id": 1412356,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532998380.771, "dur": 8.886, + "args": { + "External id": 1412357,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532998392.399, "dur": 3.578, + "args": { + "External id": 1412358,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532998397.697, "dur": 2.057, + "args": { + "External id": 1412359,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532998401.284, "dur": 4.740, + "args": { + "External id": 1412360,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532998476.750, "dur": 6.170, + "args": { + "External id": 1412361,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532998478.887, "dur": 3.627, + "args": { + "External id": 1412362,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532998487.317, "dur": 41.927, + "args": { + "External id": 1412363,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532998494.117, "dur": 4.615, + "args": { + "External id": 1412364,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410532998530.826, "dur": 1.690, + "args": { + "External id": 1412365,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532998531.731, "dur": 0.706, + "args": { + "External id": 1412366,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410532998533.671, "dur": 16.638, + "args": { + "External id": 1412367,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410532998536.374, "dur": 0.686, + "args": { + "External id": 1412368,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410532998651.341, "dur": 31.483, + "args": { + "External id": 1412369,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532998705.646, "dur": 17.659, + "args": { + "External id": 1412370,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532998732.631, "dur": 52.976, + "args": { + "External id": 1412371,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532998792.668, "dur": 43.530, + "args": { + "External id": 1412372,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532998847.076, "dur": 27.313, + "args": { + "External id": 1412373,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532998880.837, "dur": 33.852, + "args": { + "External id": 1412374,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532998925.456, "dur": 30.362, + "args": { + "External id": 1412375,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410532998963.445, "dur": 33.339, + "args": { + "External id": 1412376,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410532999022.486, "dur": 25.839, + "args": { + "External id": 1412377,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532999107.958, "dur": 34.133, + "args": { + "External id": 1412378,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410532999165.988, "dur": 20.436, + "args": { + "External id": 1412379,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410532999209.220, "dur": 16.778, + "args": { + "External id": 1412380,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410532999242.375, "dur": 18.944, + "args": { + "External id": 1412381,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999348.306, "dur": 16.957, + "args": { + "External id": 1412382,"Record function id": 0, "Ev Idx": 4893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999351.749, "dur": 12.511, + "args": { + "External id": 1412383,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999356.371, "dur": 6.407, + "args": { + "External id": 1412384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999358.226, "dur": 4.433, + "args": { + "External id": 1412385,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999369.994, "dur": 6.051, + "args": { + "External id": 1412386,"Record function id": 0, "Ev Idx": 4897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999371.778, "dur": 3.776, + "args": { + "External id": 1412387,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999372.807, "dur": 2.037, + "args": { + "External id": 1412388,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999373.559, "dur": 1.114, + "args": { + "External id": 1412389,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999379.917, "dur": 7.901, + "args": { + "External id": 1412390,"Record function id": 0, "Ev Idx": 4901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999381.712, "dur": 5.582, + "args": { + "External id": 1412391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999382.453, "dur": 4.348, + "args": { + "External id": 1412392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999383.415, "dur": 3.273, + "args": { + "External id": 1412393,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999391.619, "dur": 5.327, + "args": { + "External id": 1412394,"Record function id": 0, "Ev Idx": 4905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999393.219, "dur": 3.213, + "args": { + "External id": 1412395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999394.256, "dur": 1.567, + "args": { + "External id": 1412396,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999394.719, "dur": 0.985, + "args": { + "External id": 1412397,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999400.626, "dur": 5.206, + "args": { + "External id": 1412398,"Record function id": 0, "Ev Idx": 4909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999402.335, "dur": 2.988, + "args": { + "External id": 1412399,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999403.165, "dur": 1.608, + "args": { + "External id": 1412400,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999403.805, "dur": 0.888, + "args": { + "External id": 1412401,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999409.498, "dur": 4.475, + "args": { + "External id": 1412402,"Record function id": 0, "Ev Idx": 4913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999410.719, "dur": 2.774, + "args": { + "External id": 1412403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999411.396, "dur": 1.576, + "args": { + "External id": 1412404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999411.846, "dur": 1.006, + "args": { + "External id": 1412405,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999437.159, "dur": 8.051, + "args": { + "External id": 1412406,"Record function id": 0, "Ev Idx": 4917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999439.439, "dur": 5.048, + "args": { + "External id": 1412407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999440.559, "dur": 2.974, + "args": { + "External id": 1412408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999441.686, "dur": 1.612, + "args": { + "External id": 1412409,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999449.705, "dur": 6.992, + "args": { + "External id": 1412410,"Record function id": 0, "Ev Idx": 4921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999451.126, "dur": 5.117, + "args": { + "External id": 1412411,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999451.846, "dur": 3.903, + "args": { + "External id": 1412412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999454.544, "dur": 1.085, + "args": { + "External id": 1412413,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999460.522, "dur": 4.655, + "args": { + "External id": 1412414,"Record function id": 0, "Ev Idx": 4925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410532999462.039, "dur": 2.665, + "args": { + "External id": 1412415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999462.741, "dur": 1.478, + "args": { + "External id": 1412416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410532999463.245, "dur": 0.868, + "args": { + "External id": 1412417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532999470.550, "dur": 76997.660, + "args": { + "External id": 1412418,"Record function id": 0, "Sequence number": 15108853, "Fwd thread id": 1, "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410532999472.869, "dur": 76983.369, + "args": { + "External id": 1412419,"Sequence number": 15108853, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4930 + } + }, + { + "ph": "f", "id": 213, "pid": 2338710, "tid": 2379450, "ts": 6410532999472.869, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410532999509.353, "dur": 46.379, + "args": { + "External id": 1412420,"Record function id": 0, "Ev Idx": 4931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410532999565.506, "dur": 76.412, + "args": { + "External id": 1412421,"Record function id": 0, "Ev Idx": 4932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410532999649.059, "dur": 76796.603, + "args": { + "External id": 1412422,"Record function id": 0, "Ev Idx": 4933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532999759.645, "dur": 9.236, + "args": { + "External id": 1412423,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410532999782.783, "dur": 8.393, + "args": { + "External id": 1412424,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532999814.700, "dur": 75534.064, + "args": { + "External id": 1412425,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410532999835.194, "dur": 75497.533, + "args": { + "External id": 1412426,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410532999959.425, "dur": 27.296, + "args": { + "External id": 1412427,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533000028.965, "dur": 75244.685, + "args": { + "External id": 1412428,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533000036.589, "dur": 75235.746, + "args": { + "External id": 1412429,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533000046.472, "dur": 61.956, + "args": { + "External id": 1412430,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533000113.361, "dur": 75152.032, + "args": { + "External id": 1412431,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533075498.973, "dur": 15.969, + "args": { + "External id": 1412432,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533075503.246, "dur": 11.128, + "args": { + "External id": 1412433,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533075552.449, "dur": 466.824, + "args": { + "External id": 1412434,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533075590.389, "dur": 422.647, + "args": { + "External id": 1412435,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4946, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533075605.592, "dur": 401.314, + "args": { + "External id": 1412436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533076045.317, "dur": 2.685, + "args": { + "External id": 1412437,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4948, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076185.509, "dur": 8.018, + "args": { + "External id": 1412438,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076249.187, "dur": 1.713, + "args": { + "External id": 1412439,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076268.189, "dur": 3.674, + "args": { + "External id": 1412440,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076285.036, "dur": 0.953, + "args": { + "External id": 1412441,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076297.413, "dur": 1.055, + "args": { + "External id": 1412442,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076310.275, "dur": 0.806, + "args": { + "External id": 1412443,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076325.776, "dur": 3.688, + "args": { + "External id": 1412444,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076340.829, "dur": 2.308, + "args": { + "External id": 1412445,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076354.748, "dur": 0.820, + "args": { + "External id": 1412446,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533076488.694, "dur": 3444.062, + "args": { + "External id": 1412447,"Record function id": 0, "Ev Idx": 4958 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410533076513.328, "dur": 1295.163, + "args": { + "External id": 1412448,"Record function id": 0, "Ev Idx": 4959 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410533076532.376, "dur": 402.487, + "args": { + "External id": 1412449,"Record function id": 0, "Ev Idx": 4960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076653.124, "dur": 5.562, + "args": { + "External id": 1412450,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076662.487, "dur": 0.839, + "args": { + "External id": 1412451,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076665.157, "dur": 3.433, + "args": { + "External id": 1412452,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076672.707, "dur": 0.911, + "args": { + "External id": 1412453,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076675.170, "dur": 1.031, + "args": { + "External id": 1412454,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076677.977, "dur": 0.935, + "args": { + "External id": 1412455,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076680.678, "dur": 2.113, + "args": { + "External id": 1412456,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076686.691, "dur": 0.781, + "args": { + "External id": 1412457,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076689.443, "dur": 0.977, + "args": { + "External id": 1412458,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533076692.183, "dur": 0.913, + "args": { + "External id": 1412459,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533076714.870, "dur": 183.570, + "args": { + "External id": 1412460,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533076734.303, "dur": 158.586, + "args": { + "External id": 1412461,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533076757.813, "dur": 20.151, + "args": { + "External id": 1412462,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533076784.932, "dur": 75.431, + "args": { + "External id": 1412463,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533076787.634, "dur": 72.330, + "args": { + "External id": 1412464,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533076792.106, "dur": 5.967, + "args": { + "External id": 1412465,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533076800.039, "dur": 59.101, + "args": { + "External id": 1412466,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.3", "pid": 2338710, "tid": 2379450, + "ts": 6410533077035.689, "dur": 763.375, + "args": { + "External id": 1412467,"Record function id": 0, "Ev Idx": 4978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410533077094.749, "dur": 690.063, + "args": { + "External id": 1412468,"Record function id": 0, "Ev Idx": 4979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533077180.788, "dur": 8.452, + "args": { + "External id": 1412469,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410533077206.837, "dur": 39.189, + "args": { + "External id": 1412470,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077212.963, "dur": 3.393, + "args": { + "External id": 1412471,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077218.453, "dur": 0.437, + "args": { + "External id": 1412472,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077220.896, "dur": 0.455, + "args": { + "External id": 1412473,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077224.633, "dur": 0.285, + "args": { + "External id": 1412474,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077226.402, "dur": 0.396, + "args": { + "External id": 1412475,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077228.265, "dur": 2.890, + "args": { + "External id": 1412476,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077234.369, "dur": 0.479, + "args": { + "External id": 1412477,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077236.669, "dur": 0.572, + "args": { + "External id": 1412478,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077238.752, "dur": 1.831, + "args": { + "External id": 1412479,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533077258.217, "dur": 54.679, + "args": { + "External id": 1412480,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410533077350.641, "dur": 156.321, + "args": { + "External id": 1412481,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533077363.110, "dur": 4.711, + "args": { + "External id": 1412482,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410533077373.639, "dur": 11.268, + "args": { + "External id": 1412483,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410533077378.329, "dur": 6.110, + "args": { + "External id": 1412484,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077382.396, "dur": 0.656, + "args": { + "External id": 1412485,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410533077393.192, "dur": 48.857, + "args": { + "External id": 1412486,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077396.346, "dur": 0.547, + "args": { + "External id": 1412487,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077399.044, "dur": 0.449, + "args": { + "External id": 1412488,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077401.405, "dur": 3.828, + "args": { + "External id": 1412489,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077407.495, "dur": 0.369, + "args": { + "External id": 1412490,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077409.611, "dur": 0.400, + "args": { + "External id": 1412491,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077412.898, "dur": 0.278, + "args": { + "External id": 1412492,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077430.949, "dur": 0.609, + "args": { + "External id": 1412493,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077433.963, "dur": 0.466, + "args": { + "External id": 1412494,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533077436.672, "dur": 0.345, + "args": { + "External id": 1412495,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533077458.015, "dur": 39.518, + "args": { + "External id": 1412496,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533077561.461, "dur": 138.698, + "args": { + "External id": 1412497,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533077595.636, "dur": 100.536, + "args": { + "External id": 1412498,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5009, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533077606.542, "dur": 84.799, + "args": { + "External id": 1412499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 5010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533077721.875, "dur": 1.948, + "args": { + "External id": 1412500,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5011, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533077816.865, "dur": 2093.158, + "args": { + "External id": 1412501,"Sequence number": 15108852, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5012 + } + }, + { + "ph": "f", "id": 214, "pid": 2338710, "tid": 2379450, "ts": 6410533077816.865, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533077944.205, "dur": 165.785, + "args": { + "External id": 1412502,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533078167.504, "dur": 51.058, + "args": { + "External id": 1412503,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410533078240.883, "dur": 67.928, + "args": { + "External id": 1412504,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533078323.028, "dur": 39.235, + "args": { + "External id": 1412505,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533078369.813, "dur": 36.278, + "args": { + "External id": 1412506,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533078413.718, "dur": 52.931, + "args": { + "External id": 1412507,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533078478.643, "dur": 32.886, + "args": { + "External id": 1412508,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533078545.038, "dur": 30.974, + "args": { + "External id": 1412509,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533078608.546, "dur": 32.910, + "args": { + "External id": 1412510,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533078670.818, "dur": 24.415, + "args": { + "External id": 1412511,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533078710.263, "dur": 17.354, + "args": { + "External id": 1412512,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533078736.629, "dur": 46.175, + "args": { + "External id": 1412513,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533078787.003, "dur": 38.319, + "args": { + "External id": 1412514,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410533078860.277, "dur": 364.751, + "args": { + "External id": 1412515,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533078972.055, "dur": 8.867, + "args": { + "External id": 1412516,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533078983.743, "dur": 3.053, + "args": { + "External id": 1412517,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533078988.528, "dur": 2.347, + "args": { + "External id": 1412518,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533078992.194, "dur": 3.308, + "args": { + "External id": 1412519,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533079051.288, "dur": 46.297, + "args": { + "External id": 1412520,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533079053.609, "dur": 43.232, + "args": { + "External id": 1412521,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533079100.881, "dur": 43.860, + "args": { + "External id": 1412522,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533079109.628, "dur": 4.004, + "args": { + "External id": 1412523,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533079149.403, "dur": 1.707, + "args": { + "External id": 1412524,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533079150.232, "dur": 0.762, + "args": { + "External id": 1412525,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533079152.336, "dur": 20.638, + "args": { + "External id": 1412526,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533079156.806, "dur": 0.816, + "args": { + "External id": 1412527,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533079275.037, "dur": 32.961, + "args": { + "External id": 1412528,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533079328.509, "dur": 18.480, + "args": { + "External id": 1412529,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533079356.446, "dur": 75.424, + "args": { + "External id": 1412530,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533079442.474, "dur": 52.051, + "args": { + "External id": 1412531,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533079506.689, "dur": 26.460, + "args": { + "External id": 1412532,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533079540.142, "dur": 36.118, + "args": { + "External id": 1412533,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533079584.585, "dur": 31.042, + "args": { + "External id": 1412534,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533079623.939, "dur": 34.079, + "args": { + "External id": 1412535,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410533079684.378, "dur": 29.917, + "args": { + "External id": 1412536,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533079734.758, "dur": 29.200, + "args": { + "External id": 1412537,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533079783.486, "dur": 19.863, + "args": { + "External id": 1412538,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533079826.098, "dur": 17.116, + "args": { + "External id": 1412539,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410533079858.742, "dur": 17.662, + "args": { + "External id": 1412540,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533079959.068, "dur": 17.102, + "args": { + "External id": 1412541,"Record function id": 0, "Ev Idx": 5052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533079962.893, "dur": 12.230, + "args": { + "External id": 1412542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533079967.931, "dur": 6.196, + "args": { + "External id": 1412543,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533079969.743, "dur": 4.269, + "args": { + "External id": 1412544,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533079981.095, "dur": 5.676, + "args": { + "External id": 1412545,"Record function id": 0, "Ev Idx": 5056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533079983.043, "dur": 3.205, + "args": { + "External id": 1412546,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533079984.236, "dur": 1.494, + "args": { + "External id": 1412547,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533079984.690, "dur": 0.888, + "args": { + "External id": 1412548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533079990.723, "dur": 7.349, + "args": { + "External id": 1412549,"Record function id": 0, "Ev Idx": 5060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533079992.214, "dur": 5.276, + "args": { + "External id": 1412550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533079992.926, "dur": 4.052, + "args": { + "External id": 1412551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533079993.798, "dur": 3.098, + "args": { + "External id": 1412552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080001.890, "dur": 4.938, + "args": { + "External id": 1412553,"Record function id": 0, "Ev Idx": 5064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080003.480, "dur": 2.855, + "args": { + "External id": 1412554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080004.370, "dur": 1.442, + "args": { + "External id": 1412555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080004.876, "dur": 0.821, + "args": { + "External id": 1412556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080010.429, "dur": 4.449, + "args": { + "External id": 1412557,"Record function id": 0, "Ev Idx": 5068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080011.988, "dur": 2.361, + "args": { + "External id": 1412558,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080012.560, "dur": 1.290, + "args": { + "External id": 1412559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080013.083, "dur": 0.678, + "args": { + "External id": 1412560,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080018.437, "dur": 6.804, + "args": { + "External id": 1412561,"Record function id": 0, "Ev Idx": 5072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080019.850, "dur": 4.886, + "args": { + "External id": 1412562,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080020.623, "dur": 3.393, + "args": { + "External id": 1412563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080023.158, "dur": 0.780, + "args": { + "External id": 1412564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080028.953, "dur": 4.415, + "args": { + "External id": 1412565,"Record function id": 0, "Ev Idx": 5076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080030.537, "dur": 2.281, + "args": { + "External id": 1412566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080031.140, "dur": 1.194, + "args": { + "External id": 1412567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080031.506, "dur": 0.742, + "args": { + "External id": 1412568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080037.616, "dur": 4.990, + "args": { + "External id": 1412569,"Record function id": 0, "Ev Idx": 5080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080039.250, "dur": 2.833, + "args": { + "External id": 1412570,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080040.322, "dur": 1.289, + "args": { + "External id": 1412571,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080040.695, "dur": 0.839, + "args": { + "External id": 1412572,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080046.480, "dur": 4.384, + "args": { + "External id": 1412573,"Record function id": 0, "Ev Idx": 5084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533080048.041, "dur": 2.337, + "args": { + "External id": 1412574,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080048.637, "dur": 1.266, + "args": { + "External id": 1412575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533080049.051, "dur": 0.722, + "args": { + "External id": 1412576,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533080093.877, "dur": 75373.794, + "args": { + "External id": 1412577,"Record function id": 0, "Sequence number": 15108851, "Fwd thread id": 1, "Ev Idx": 5088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533080097.442, "dur": 75359.517, + "args": { + "External id": 1412578,"Sequence number": 15108851, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5089 + } + }, + { + "ph": "f", "id": 215, "pid": 2338710, "tid": 2379450, "ts": 6410533080097.442, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410533080136.691, "dur": 48.475, + "args": { + "External id": 1412579,"Record function id": 0, "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410533080195.354, "dur": 78.207, + "args": { + "External id": 1412580,"Record function id": 0, "Ev Idx": 5091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410533080280.715, "dur": 75165.709, + "args": { + "External id": 1412581,"Record function id": 0, "Ev Idx": 5092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533080385.878, "dur": 9.433, + "args": { + "External id": 1412582,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533080407.107, "dur": 23.684, + "args": { + "External id": 1412583,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533080452.928, "dur": 73985.742, + "args": { + "External id": 1412584,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533080469.634, "dur": 73940.832, + "args": { + "External id": 1412585,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533080577.165, "dur": 33.293, + "args": { + "External id": 1412586,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533080638.791, "dur": 73715.721, + "args": { + "External id": 1412587,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533080642.145, "dur": 73710.761, + "args": { + "External id": 1412588,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533080648.328, "dur": 20.282, + "args": { + "External id": 1412589,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533080670.831, "dur": 73675.476, + "args": { + "External id": 1412590,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533154571.956, "dur": 15.066, + "args": { + "External id": 1412591,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533154576.353, "dur": 10.102, + "args": { + "External id": 1412592,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533154623.842, "dur": 423.405, + "args": { + "External id": 1412593,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533154663.282, "dur": 378.057, + "args": { + "External id": 1412594,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5105, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533154678.908, "dur": 355.921, + "args": { + "External id": 1412595,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533155114.250, "dur": 3.559, + "args": { + "External id": 1412596,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5107, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155194.481, "dur": 7.915, + "args": { + "External id": 1412597,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155254.764, "dur": 1.389, + "args": { + "External id": 1412598,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155273.689, "dur": 3.924, + "args": { + "External id": 1412599,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155290.128, "dur": 1.083, + "args": { + "External id": 1412600,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155303.288, "dur": 1.010, + "args": { + "External id": 1412601,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155315.149, "dur": 1.054, + "args": { + "External id": 1412602,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155328.100, "dur": 3.151, + "args": { + "External id": 1412603,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155343.317, "dur": 2.214, + "args": { + "External id": 1412604,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155358.589, "dur": 0.980, + "args": { + "External id": 1412605,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533155486.622, "dur": 3449.329, + "args": { + "External id": 1412606,"Record function id": 0, "Ev Idx": 5117 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410533155510.482, "dur": 1319.848, + "args": { + "External id": 1412607,"Record function id": 0, "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410533155528.857, "dur": 424.362, + "args": { + "External id": 1412608,"Record function id": 0, "Ev Idx": 5119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155671.720, "dur": 5.702, + "args": { + "External id": 1412609,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155681.912, "dur": 0.961, + "args": { + "External id": 1412610,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155685.138, "dur": 3.412, + "args": { + "External id": 1412611,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155692.570, "dur": 0.856, + "args": { + "External id": 1412612,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155695.037, "dur": 0.799, + "args": { + "External id": 1412613,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155697.662, "dur": 0.749, + "args": { + "External id": 1412614,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155700.363, "dur": 1.755, + "args": { + "External id": 1412615,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155705.651, "dur": 0.842, + "args": { + "External id": 1412616,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155708.286, "dur": 0.729, + "args": { + "External id": 1412617,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533155710.587, "dur": 0.626, + "args": { + "External id": 1412618,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533155732.845, "dur": 182.909, + "args": { + "External id": 1412619,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533155752.890, "dur": 156.974, + "args": { + "External id": 1412620,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533155773.342, "dur": 18.271, + "args": { + "External id": 1412621,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533155796.168, "dur": 78.120, + "args": { + "External id": 1412622,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 5133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533155798.960, "dur": 74.981, + "args": { + "External id": 1412623,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 5134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533155803.942, "dur": 6.405, + "args": { + "External id": 1412624,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533155812.187, "dur": 60.891, + "args": { + "External id": 1412625,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 5136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.2", "pid": 2338710, "tid": 2379450, + "ts": 6410533156098.303, "dur": 723.160, + "args": { + "External id": 1412626,"Record function id": 0, "Ev Idx": 5137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410533156120.569, "dur": 686.477, + "args": { + "External id": 1412627,"Record function id": 0, "Ev Idx": 5138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533156201.949, "dur": 7.570, + "args": { + "External id": 1412628,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410533156227.769, "dur": 37.664, + "args": { + "External id": 1412629,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156233.736, "dur": 2.161, + "args": { + "External id": 1412630,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156238.327, "dur": 1.977, + "args": { + "External id": 1412631,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156242.025, "dur": 0.674, + "args": { + "External id": 1412632,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156244.467, "dur": 0.787, + "args": { + "External id": 1412633,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156248.428, "dur": 0.327, + "args": { + "External id": 1412634,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156250.378, "dur": 2.883, + "args": { + "External id": 1412635,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156254.381, "dur": 0.422, + "args": { + "External id": 1412636,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156257.547, "dur": 0.345, + "args": { + "External id": 1412637,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156259.770, "dur": 0.360, + "args": { + "External id": 1412638,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533156278.313, "dur": 53.947, + "args": { + "External id": 1412639,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410533156370.063, "dur": 156.288, + "args": { + "External id": 1412640,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 5151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533156381.708, "dur": 4.695, + "args": { + "External id": 1412641,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410533156392.560, "dur": 11.244, + "args": { + "External id": 1412642,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410533156397.346, "dur": 5.990, + "args": { + "External id": 1412643,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 5154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156401.418, "dur": 0.543, + "args": { + "External id": 1412644,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410533156412.303, "dur": 48.726, + "args": { + "External id": 1412645,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156431.393, "dur": 0.834, + "args": { + "External id": 1412646,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156436.106, "dur": 0.347, + "args": { + "External id": 1412647,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156438.065, "dur": 3.014, + "args": { + "External id": 1412648,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156442.501, "dur": 1.762, + "args": { + "External id": 1412649,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156445.999, "dur": 0.454, + "args": { + "External id": 1412650,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156448.371, "dur": 0.382, + "args": { + "External id": 1412651,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156451.938, "dur": 0.480, + "args": { + "External id": 1412652,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156453.866, "dur": 0.467, + "args": { + "External id": 1412653,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533156456.309, "dur": 0.289, + "args": { + "External id": 1412654,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533156480.119, "dur": 36.505, + "args": { + "External id": 1412655,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533156582.391, "dur": 141.839, + "args": { + "External id": 1412656,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 5167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533156618.891, "dur": 101.032, + "args": { + "External id": 1412657,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5168, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533156630.851, "dur": 84.383, + "args": { + "External id": 1412658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 5169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533156744.968, "dur": 2.319, + "args": { + "External id": 1412659,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5170, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533156838.975, "dur": 2072.119, + "args": { + "External id": 1412660,"Sequence number": 15108850, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5171 + } + }, + { + "ph": "f", "id": 216, "pid": 2338710, "tid": 2379450, "ts": 6410533156838.975, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533156968.010, "dur": 167.988, + "args": { + "External id": 1412661,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533157191.423, "dur": 48.206, + "args": { + "External id": 1412662,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410533157261.182, "dur": 66.509, + "args": { + "External id": 1412663,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533157341.498, "dur": 37.680, + "args": { + "External id": 1412664,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533157386.270, "dur": 55.799, + "args": { + "External id": 1412665,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533157453.461, "dur": 36.521, + "args": { + "External id": 1412666,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533157499.267, "dur": 32.208, + "args": { + "External id": 1412667,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533157564.961, "dur": 29.468, + "args": { + "External id": 1412668,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533157616.628, "dur": 32.866, + "args": { + "External id": 1412669,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533157678.595, "dur": 22.934, + "args": { + "External id": 1412670,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533157716.293, "dur": 16.589, + "args": { + "External id": 1412671,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533157750.374, "dur": 42.395, + "args": { + "External id": 1412672,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533157796.404, "dur": 35.994, + "args": { + "External id": 1412673,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410533157866.758, "dur": 369.418, + "args": { + "External id": 1412674,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533157964.858, "dur": 6.343, + "args": { + "External id": 1412675,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533157973.764, "dur": 3.377, + "args": { + "External id": 1412676,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533157981.223, "dur": 2.368, + "args": { + "External id": 1412677,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533157996.209, "dur": 7.440, + "args": { + "External id": 1412678,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533158091.533, "dur": 7.303, + "args": { + "External id": 1412679,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533158094.796, "dur": 3.590, + "args": { + "External id": 1412680,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533158101.103, "dur": 45.271, + "args": { + "External id": 1412681,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533158108.040, "dur": 5.704, + "args": { + "External id": 1412682,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533158148.309, "dur": 1.971, + "args": { + "External id": 1412683,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533158149.596, "dur": 0.608, + "args": { + "External id": 1412684,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533158151.314, "dur": 17.869, + "args": { + "External id": 1412685,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533158155.472, "dur": 0.568, + "args": { + "External id": 1412686,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533158286.236, "dur": 34.976, + "args": { + "External id": 1412687,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533158342.663, "dur": 17.386, + "args": { + "External id": 1412688,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533158370.137, "dur": 78.086, + "args": { + "External id": 1412689,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533158458.690, "dur": 48.719, + "args": { + "External id": 1412690,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533158520.558, "dur": 24.459, + "args": { + "External id": 1412691,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533158551.251, "dur": 33.945, + "args": { + "External id": 1412692,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533158593.524, "dur": 31.186, + "args": { + "External id": 1412693,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533158632.363, "dur": 32.526, + "args": { + "External id": 1412694,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410533158691.797, "dur": 29.787, + "args": { + "External id": 1412695,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533158742.018, "dur": 28.621, + "args": { + "External id": 1412696,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533158788.437, "dur": 20.213, + "args": { + "External id": 1412697,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533158830.350, "dur": 15.442, + "args": { + "External id": 1412698,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410533158861.754, "dur": 16.730, + "args": { + "External id": 1412699,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533158962.582, "dur": 16.530, + "args": { + "External id": 1412700,"Record function id": 0, "Ev Idx": 5211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533158966.385, "dur": 11.740, + "args": { + "External id": 1412701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533158971.076, "dur": 5.937, + "args": { + "External id": 1412702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533158972.624, "dur": 4.276, + "args": { + "External id": 1412703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533158983.634, "dur": 5.888, + "args": { + "External id": 1412704,"Record function id": 0, "Ev Idx": 5215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533158985.527, "dur": 3.314, + "args": { + "External id": 1412705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533158986.518, "dur": 1.644, + "args": { + "External id": 1412706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533158987.178, "dur": 0.846, + "args": { + "External id": 1412707,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533158993.590, "dur": 7.531, + "args": { + "External id": 1412708,"Record function id": 0, "Ev Idx": 5219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533158995.190, "dur": 5.448, + "args": { + "External id": 1412709,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533158995.771, "dur": 4.367, + "args": { + "External id": 1412710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533158996.631, "dur": 3.426, + "args": { + "External id": 1412711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159004.934, "dur": 5.069, + "args": { + "External id": 1412712,"Record function id": 0, "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159006.849, "dur": 2.628, + "args": { + "External id": 1412713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159007.504, "dur": 1.439, + "args": { + "External id": 1412714,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159007.941, "dur": 0.917, + "args": { + "External id": 1412715,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159013.676, "dur": 4.619, + "args": { + "External id": 1412716,"Record function id": 0, "Ev Idx": 5227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159015.478, "dur": 2.318, + "args": { + "External id": 1412717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159016.078, "dur": 1.210, + "args": { + "External id": 1412718,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159016.430, "dur": 0.737, + "args": { + "External id": 1412719,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159022.080, "dur": 6.696, + "args": { + "External id": 1412720,"Record function id": 0, "Ev Idx": 5231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159023.470, "dur": 4.821, + "args": { + "External id": 1412721,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159024.109, "dur": 3.682, + "args": { + "External id": 1412722,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159026.971, "dur": 0.734, + "args": { + "External id": 1412723,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159032.584, "dur": 4.667, + "args": { + "External id": 1412724,"Record function id": 0, "Ev Idx": 5235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159034.287, "dur": 2.379, + "args": { + "External id": 1412725,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159034.828, "dur": 1.341, + "args": { + "External id": 1412726,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159035.354, "dur": 0.731, + "args": { + "External id": 1412727,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159040.891, "dur": 4.534, + "args": { + "External id": 1412728,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159042.339, "dur": 2.618, + "args": { + "External id": 1412729,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159042.898, "dur": 1.559, + "args": { + "External id": 1412730,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159043.486, "dur": 0.878, + "args": { + "External id": 1412731,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159049.478, "dur": 4.551, + "args": { + "External id": 1412732,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533159051.086, "dur": 2.466, + "args": { + "External id": 1412733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159051.666, "dur": 1.352, + "args": { + "External id": 1412734,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533159052.174, "dur": 0.756, + "args": { + "External id": 1412735,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533159097.575, "dur": 70705.161, + "args": { + "External id": 1412736,"Record function id": 0, "Sequence number": 15108849, "Fwd thread id": 1, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533159101.033, "dur": 70690.889, + "args": { + "External id": 1412737,"Sequence number": 15108849, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5248 + } + }, + { + "ph": "f", "id": 217, "pid": 2338710, "tid": 2379450, "ts": 6410533159101.033, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410533159138.942, "dur": 48.045, + "args": { + "External id": 1412738,"Record function id": 0, "Ev Idx": 5249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410533159196.927, "dur": 73.437, + "args": { + "External id": 1412739,"Record function id": 0, "Ev Idx": 5250 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410533159277.988, "dur": 70504.675, + "args": { + "External id": 1412740,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533159385.338, "dur": 8.891, + "args": { + "External id": 1412741,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533159405.528, "dur": 8.016, + "args": { + "External id": 1412742,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533159449.783, "dur": 69383.414, + "args": { + "External id": 1412743,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533159466.747, "dur": 69351.129, + "args": { + "External id": 1412744,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533159571.065, "dur": 22.518, + "args": { + "External id": 1412745,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533159616.736, "dur": 69142.820, + "args": { + "External id": 1412746,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533159620.075, "dur": 69137.814, + "args": { + "External id": 1412747,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533159625.152, "dur": 14.832, + "args": { + "External id": 1412748,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533159642.443, "dur": 69107.662, + "args": { + "External id": 1412749,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533228964.888, "dur": 19.010, + "args": { + "External id": 1412750,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533228969.394, "dur": 14.072, + "args": { + "External id": 1412751,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533229018.545, "dur": 415.568, + "args": { + "External id": 1412752,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533229096.961, "dur": 316.267, + "args": { + "External id": 1412753,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5264, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533229115.332, "dur": 291.830, + "args": { + "External id": 1412754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533229463.777, "dur": 3.439, + "args": { + "External id": 1412755,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5266, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229543.016, "dur": 8.158, + "args": { + "External id": 1412756,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229602.040, "dur": 1.615, + "args": { + "External id": 1412757,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229621.464, "dur": 4.068, + "args": { + "External id": 1412758,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229638.289, "dur": 0.880, + "args": { + "External id": 1412759,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229652.203, "dur": 1.061, + "args": { + "External id": 1412760,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229665.827, "dur": 1.108, + "args": { + "External id": 1412761,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229679.309, "dur": 3.223, + "args": { + "External id": 1412762,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229694.760, "dur": 2.556, + "args": { + "External id": 1412763,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533229711.263, "dur": 0.755, + "args": { + "External id": 1412764,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533229820.400, "dur": 3465.988, + "args": { + "External id": 1412765,"Record function id": 0, "Ev Idx": 5276 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410533229844.636, "dur": 1347.637, + "args": { + "External id": 1412766,"Record function id": 0, "Ev Idx": 5277 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410533229862.196, "dur": 434.495, + "args": { + "External id": 1412767,"Record function id": 0, "Ev Idx": 5278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533229972.212, "dur": 4.396, + "args": { + "External id": 1412768,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533229980.163, "dur": 1.316, + "args": { + "External id": 1412769,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533229983.597, "dur": 3.233, + "args": { + "External id": 1412770,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533229988.731, "dur": 0.954, + "args": { + "External id": 1412771,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533229991.387, "dur": 0.911, + "args": { + "External id": 1412772,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533229996.640, "dur": 0.750, + "args": { + "External id": 1412773,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533229999.292, "dur": 2.171, + "args": { + "External id": 1412774,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533230003.620, "dur": 0.752, + "args": { + "External id": 1412775,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533230006.143, "dur": 0.955, + "args": { + "External id": 1412776,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533230011.243, "dur": 1.004, + "args": { + "External id": 1412777,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533230033.292, "dur": 220.878, + "args": { + "External id": 1412778,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533230092.066, "dur": 155.416, + "args": { + "External id": 1412779,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533230114.684, "dur": 17.713, + "args": { + "External id": 1412780,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533230137.110, "dur": 77.729, + "args": { + "External id": 1412781,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 5292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533230139.897, "dur": 74.510, + "args": { + "External id": 1412782,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 5293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230144.748, "dur": 7.754, + "args": { + "External id": 1412783,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533230154.497, "dur": 59.096, + "args": { + "External id": 1412784,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 5295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.1", "pid": 2338710, "tid": 2379450, + "ts": 6410533230409.075, "dur": 774.181, + "args": { + "External id": 1412785,"Record function id": 0, "Ev Idx": 5296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410533230449.700, "dur": 717.998, + "args": { + "External id": 1412786,"Record function id": 0, "Ev Idx": 5297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533230529.407, "dur": 7.090, + "args": { + "External id": 1412787,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410533230554.367, "dur": 44.904, + "args": { + "External id": 1412788,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230560.404, "dur": 3.259, + "args": { + "External id": 1412789,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230571.633, "dur": 0.498, + "args": { + "External id": 1412790,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230573.645, "dur": 0.365, + "args": { + "External id": 1412791,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230577.553, "dur": 0.450, + "args": { + "External id": 1412792,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230579.853, "dur": 0.419, + "args": { + "External id": 1412793,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230581.732, "dur": 4.175, + "args": { + "External id": 1412794,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230587.482, "dur": 0.414, + "args": { + "External id": 1412795,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230589.928, "dur": 0.644, + "args": { + "External id": 1412796,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230593.760, "dur": 0.290, + "args": { + "External id": 1412797,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533230612.371, "dur": 56.671, + "args": { + "External id": 1412798,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410533230707.460, "dur": 133.951, + "args": { + "External id": 1412799,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 5310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533230719.530, "dur": 4.330, + "args": { + "External id": 1412800,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410533230729.724, "dur": 14.901, + "args": { + "External id": 1412801,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410533230737.048, "dur": 6.953, + "args": { + "External id": 1412802,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 5313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230741.863, "dur": 0.655, + "args": { + "External id": 1412803,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410533230753.314, "dur": 30.096, + "args": { + "External id": 1412804,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230756.056, "dur": 0.535, + "args": { + "External id": 1412805,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230758.692, "dur": 0.528, + "args": { + "External id": 1412806,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230762.214, "dur": 2.477, + "args": { + "External id": 1412807,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230766.370, "dur": 0.368, + "args": { + "External id": 1412808,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230768.448, "dur": 0.386, + "args": { + "External id": 1412809,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230771.771, "dur": 0.373, + "args": { + "External id": 1412810,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230773.974, "dur": 0.368, + "args": { + "External id": 1412811,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230776.145, "dur": 1.856, + "args": { + "External id": 1412812,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533230779.398, "dur": 0.267, + "args": { + "External id": 1412813,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533230797.199, "dur": 35.495, + "args": { + "External id": 1412814,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533230894.361, "dur": 140.004, + "args": { + "External id": 1412815,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 5326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533230928.644, "dur": 101.702, + "args": { + "External id": 1412816,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5327, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533230939.754, "dur": 86.073, + "args": { + "External id": 1412817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 5328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533231054.784, "dur": 43.942, + "args": { + "External id": 1412818,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5329, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533231200.972, "dur": 2061.031, + "args": { + "External id": 1412819,"Sequence number": 15108848, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5330 + } + }, + { + "ph": "f", "id": 218, "pid": 2338710, "tid": 2379450, "ts": 6410533231200.972, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533231331.062, "dur": 141.421, + "args": { + "External id": 1412820,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533231529.121, "dur": 48.184, + "args": { + "External id": 1412821,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410533231600.089, "dur": 61.712, + "args": { + "External id": 1412822,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533231675.957, "dur": 36.248, + "args": { + "External id": 1412823,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533231719.497, "dur": 35.936, + "args": { + "External id": 1412824,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533231762.453, "dur": 30.236, + "args": { + "External id": 1412825,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533231800.879, "dur": 31.818, + "args": { + "External id": 1412826,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533231863.585, "dur": 28.698, + "args": { + "External id": 1412827,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533231916.474, "dur": 32.007, + "args": { + "External id": 1412828,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533231975.530, "dur": 20.977, + "args": { + "External id": 1412829,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533232013.648, "dur": 16.857, + "args": { + "External id": 1412830,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533232040.917, "dur": 84.343, + "args": { + "External id": 1412831,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533232132.662, "dur": 40.272, + "args": { + "External id": 1412832,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410533232221.011, "dur": 339.876, + "args": { + "External id": 1412833,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533232310.574, "dur": 7.308, + "args": { + "External id": 1412834,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533232320.526, "dur": 4.597, + "args": { + "External id": 1412835,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533232326.888, "dur": 2.545, + "args": { + "External id": 1412836,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533232330.809, "dur": 3.204, + "args": { + "External id": 1412837,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533232379.107, "dur": 5.303, + "args": { + "External id": 1412838,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533232381.155, "dur": 3.073, + "args": { + "External id": 1412839,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533232387.047, "dur": 54.710, + "args": { + "External id": 1412840,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533232393.716, "dur": 3.817, + "args": { + "External id": 1412841,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533232445.197, "dur": 5.448, + "args": { + "External id": 1412842,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533232449.141, "dur": 1.382, + "args": { + "External id": 1412843,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533232451.892, "dur": 46.877, + "args": { + "External id": 1412844,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533232471.542, "dur": 2.883, + "args": { + "External id": 1412845,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533232613.848, "dur": 37.131, + "args": { + "External id": 1412846,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533232673.521, "dur": 21.007, + "args": { + "External id": 1412847,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533232703.499, "dur": 57.407, + "args": { + "External id": 1412848,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533232768.678, "dur": 46.415, + "args": { + "External id": 1412849,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533232825.783, "dur": 24.510, + "args": { + "External id": 1412850,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533232856.360, "dur": 35.502, + "args": { + "External id": 1412851,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533232899.187, "dur": 30.121, + "args": { + "External id": 1412852,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533232937.737, "dur": 32.868, + "args": { + "External id": 1412853,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410533232994.531, "dur": 26.942, + "args": { + "External id": 1412854,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533233043.546, "dur": 69.575, + "args": { + "External id": 1412855,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533233133.882, "dur": 20.279, + "args": { + "External id": 1412856,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533233179.807, "dur": 16.335, + "args": { + "External id": 1412857,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410533233211.190, "dur": 17.372, + "args": { + "External id": 1412858,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233313.116, "dur": 17.460, + "args": { + "External id": 1412859,"Record function id": 0, "Ev Idx": 5370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233317.093, "dur": 12.306, + "args": { + "External id": 1412860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233322.220, "dur": 6.105, + "args": { + "External id": 1412861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233323.681, "dur": 4.528, + "args": { + "External id": 1412862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233335.242, "dur": 5.501, + "args": { + "External id": 1412863,"Record function id": 0, "Ev Idx": 5374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233336.879, "dur": 3.305, + "args": { + "External id": 1412864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233337.913, "dur": 1.650, + "args": { + "External id": 1412865,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233338.540, "dur": 0.877, + "args": { + "External id": 1412866,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233344.803, "dur": 7.074, + "args": { + "External id": 1412867,"Record function id": 0, "Ev Idx": 5378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233346.449, "dur": 4.934, + "args": { + "External id": 1412868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233347.090, "dur": 3.787, + "args": { + "External id": 1412869,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233347.616, "dur": 3.171, + "args": { + "External id": 1412870,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233355.669, "dur": 4.587, + "args": { + "External id": 1412871,"Record function id": 0, "Ev Idx": 5382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233357.035, "dur": 2.717, + "args": { + "External id": 1412872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233357.650, "dur": 1.597, + "args": { + "External id": 1412873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233358.115, "dur": 1.017, + "args": { + "External id": 1412874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233364.044, "dur": 4.643, + "args": { + "External id": 1412875,"Record function id": 0, "Ev Idx": 5386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233365.404, "dur": 2.786, + "args": { + "External id": 1412876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233366.442, "dur": 1.241, + "args": { + "External id": 1412877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233366.814, "dur": 0.782, + "args": { + "External id": 1412878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233372.388, "dur": 6.868, + "args": { + "External id": 1412879,"Record function id": 0, "Ev Idx": 5390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233373.933, "dur": 4.810, + "args": { + "External id": 1412880,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233374.619, "dur": 3.673, + "args": { + "External id": 1412881,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233377.157, "dur": 0.996, + "args": { + "External id": 1412882,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233383.063, "dur": 4.434, + "args": { + "External id": 1412883,"Record function id": 0, "Ev Idx": 5394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233384.690, "dur": 2.309, + "args": { + "External id": 1412884,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233385.310, "dur": 1.233, + "args": { + "External id": 1412885,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233385.629, "dur": 0.786, + "args": { + "External id": 1412886,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233391.184, "dur": 4.567, + "args": { + "External id": 1412887,"Record function id": 0, "Ev Idx": 5398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233392.579, "dur": 2.657, + "args": { + "External id": 1412888,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233393.190, "dur": 1.547, + "args": { + "External id": 1412889,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233393.779, "dur": 0.872, + "args": { + "External id": 1412890,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233399.366, "dur": 4.856, + "args": { + "External id": 1412891,"Record function id": 0, "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533233400.930, "dur": 2.793, + "args": { + "External id": 1412892,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233401.979, "dur": 1.286, + "args": { + "External id": 1412893,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533233402.436, "dur": 0.743, + "args": { + "External id": 1412894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533233409.637, "dur": 66457.043, + "args": { + "External id": 1412895,"Record function id": 0, "Sequence number": 15108847, "Fwd thread id": 1, "Ev Idx": 5406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533233412.040, "dur": 66441.181, + "args": { + "External id": 1412896,"Sequence number": 15108847, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5407 + } + }, + { + "ph": "f", "id": 219, "pid": 2338710, "tid": 2379450, "ts": 6410533233412.040, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410533233462.418, "dur": 47.449, + "args": { + "External id": 1412897,"Record function id": 0, "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410533233519.933, "dur": 80.220, + "args": { + "External id": 1412898,"Record function id": 0, "Ev Idx": 5409 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410533233607.906, "dur": 66232.754, + "args": { + "External id": 1412899,"Record function id": 0, "Ev Idx": 5410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533233716.102, "dur": 9.011, + "args": { + "External id": 1412900,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533233736.838, "dur": 7.765, + "args": { + "External id": 1412901,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533233760.548, "dur": 64686.329, + "args": { + "External id": 1412902,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533233778.802, "dur": 64632.705, + "args": { + "External id": 1412903,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533233876.431, "dur": 20.393, + "args": { + "External id": 1412904,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533233920.592, "dur": 64413.045, + "args": { + "External id": 1412905,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533233925.477, "dur": 64406.580, + "args": { + "External id": 1412906,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533233931.218, "dur": 9.857, + "args": { + "External id": 1412907,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533233943.636, "dur": 64379.828, + "args": { + "External id": 1412908,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533298609.191, "dur": 20.399, + "args": { + "External id": 1412909,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533298614.831, "dur": 13.846, + "args": { + "External id": 1412910,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533298673.054, "dur": 653.040, + "args": { + "External id": 1412911,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533298718.911, "dur": 597.910, + "args": { + "External id": 1412912,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5423, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533298738.917, "dur": 565.941, + "args": { + "External id": 1412913,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533299367.265, "dur": 4.635, + "args": { + "External id": 1412914,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5425, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299495.719, "dur": 10.371, + "args": { + "External id": 1412915,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299575.361, "dur": 2.460, + "args": { + "External id": 1412916,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299604.648, "dur": 4.775, + "args": { + "External id": 1412917,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299631.624, "dur": 1.706, + "args": { + "External id": 1412918,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299655.715, "dur": 1.504, + "args": { + "External id": 1412919,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299676.818, "dur": 1.256, + "args": { + "External id": 1412920,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299695.297, "dur": 6.813, + "args": { + "External id": 1412921,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299719.632, "dur": 2.947, + "args": { + "External id": 1412922,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533299742.946, "dur": 1.367, + "args": { + "External id": 1412923,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533299890.695, "dur": 5254.862, + "args": { + "External id": 1412924,"Record function id": 0, "Ev Idx": 5435 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410533299921.890, "dur": 1976.275, + "args": { + "External id": 1412925,"Record function id": 0, "Ev Idx": 5436 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410533299944.421, "dur": 628.922, + "args": { + "External id": 1412926,"Record function id": 0, "Ev Idx": 5437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300136.129, "dur": 7.210, + "args": { + "External id": 1412927,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300149.379, "dur": 1.618, + "args": { + "External id": 1412928,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300154.140, "dur": 3.714, + "args": { + "External id": 1412929,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300161.022, "dur": 1.524, + "args": { + "External id": 1412930,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300165.233, "dur": 1.297, + "args": { + "External id": 1412931,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300172.055, "dur": 1.322, + "args": { + "External id": 1412932,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300176.470, "dur": 2.661, + "args": { + "External id": 1412933,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300182.251, "dur": 1.536, + "args": { + "External id": 1412934,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300186.630, "dur": 1.228, + "args": { + "External id": 1412935,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533300193.547, "dur": 1.055, + "args": { + "External id": 1412936,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533300224.384, "dur": 285.750, + "args": { + "External id": 1412937,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533300263.054, "dur": 237.285, + "args": { + "External id": 1412938,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533300289.980, "dur": 23.107, + "args": { + "External id": 1412939,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533300318.551, "dur": 129.680, + "args": { + "External id": 1412940,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 5451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533300322.327, "dur": 125.174, + "args": { + "External id": 1412941,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 5452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300328.670, "dur": 10.707, + "args": { + "External id": 1412942,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533300342.147, "dur": 103.195, + "args": { + "External id": 1412943,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 5454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.0", "pid": 2338710, "tid": 2379450, + "ts": 6410533300739.869, "dur": 1148.616, + "args": { + "External id": 1412944,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410533300770.735, "dur": 1100.718, + "args": { + "External id": 1412945,"Record function id": 0, "Ev Idx": 5456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533300896.062, "dur": 16.101, + "args": { + "External id": 1412946,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410533300943.575, "dur": 60.823, + "args": { + "External id": 1412947,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300954.100, "dur": 3.040, + "args": { + "External id": 1412948,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300961.499, "dur": 2.560, + "args": { + "External id": 1412949,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300966.554, "dur": 0.636, + "args": { + "External id": 1412950,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300969.893, "dur": 0.683, + "args": { + "External id": 1412951,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300975.386, "dur": 0.549, + "args": { + "External id": 1412952,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300978.428, "dur": 3.498, + "args": { + "External id": 1412953,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300986.194, "dur": 0.920, + "args": { + "External id": 1412954,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300992.728, "dur": 0.744, + "args": { + "External id": 1412955,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533300995.679, "dur": 0.787, + "args": { + "External id": 1412956,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533301022.908, "dur": 128.489, + "args": { + "External id": 1412957,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410533301223.121, "dur": 243.975, + "args": { + "External id": 1412958,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 5469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533301244.730, "dur": 11.801, + "args": { + "External id": 1412959,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410533301265.849, "dur": 19.537, + "args": { + "External id": 1412960,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410533301272.348, "dur": 12.390, + "args": { + "External id": 1412961,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 5472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301279.920, "dur": 1.455, + "args": { + "External id": 1412962,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410533301300.000, "dur": 45.260, + "args": { + "External id": 1412963,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301304.929, "dur": 0.838, + "args": { + "External id": 1412964,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301310.044, "dur": 0.889, + "args": { + "External id": 1412965,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301313.340, "dur": 2.981, + "args": { + "External id": 1412966,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301319.464, "dur": 1.851, + "args": { + "External id": 1412967,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301324.105, "dur": 0.763, + "args": { + "External id": 1412968,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301327.663, "dur": 0.475, + "args": { + "External id": 1412969,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301332.009, "dur": 0.419, + "args": { + "External id": 1412970,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301335.533, "dur": 0.943, + "args": { + "External id": 1412971,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533301338.730, "dur": 0.407, + "args": { + "External id": 1412972,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533301367.371, "dur": 78.880, + "args": { + "External id": 1412973,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533301569.968, "dur": 190.721, + "args": { + "External id": 1412974,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 5485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533301616.941, "dur": 138.297, + "args": { + "External id": 1412975,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5486, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533301635.422, "dur": 114.399, + "args": { + "External id": 1412976,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 5487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533301786.890, "dur": 2.046, + "args": { + "External id": 1412977,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5488, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533301907.867, "dur": 3205.499, + "args": { + "External id": 1412978,"Sequence number": 15108846, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5489 + } + }, + { + "ph": "f", "id": 220, "pid": 2338710, "tid": 2379450, "ts": 6410533301907.867, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533302117.357, "dur": 171.303, + "args": { + "External id": 1412979,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533302380.978, "dur": 83.800, + "args": { + "External id": 1412980,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410533302500.631, "dur": 99.461, + "args": { + "External id": 1412981,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533302623.077, "dur": 44.031, + "args": { + "External id": 1412982,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533302676.288, "dur": 39.173, + "args": { + "External id": 1412983,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533302723.963, "dur": 32.600, + "args": { + "External id": 1412984,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533302765.353, "dur": 33.389, + "args": { + "External id": 1412985,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533302845.671, "dur": 43.329, + "args": { + "External id": 1412986,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533302920.766, "dur": 41.711, + "args": { + "External id": 1412987,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533303000.532, "dur": 31.407, + "args": { + "External id": 1412988,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533303054.208, "dur": 67.858, + "args": { + "External id": 1412989,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533303140.906, "dur": 68.300, + "args": { + "External id": 1412990,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533303214.957, "dur": 41.727, + "args": { + "External id": 1412991,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410533303310.039, "dur": 319.696, + "args": { + "External id": 1412992,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533303408.597, "dur": 28.698, + "args": { + "External id": 1412993,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533303442.037, "dur": 3.763, + "args": { + "External id": 1412994,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533303447.239, "dur": 2.528, + "args": { + "External id": 1412995,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533303450.926, "dur": 2.007, + "args": { + "External id": 1412996,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533303505.120, "dur": 7.216, + "args": { + "External id": 1412997,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533303507.204, "dur": 4.896, + "args": { + "External id": 1412998,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533303514.515, "dur": 37.400, + "args": { + "External id": 1412999,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533303520.952, "dur": 4.178, + "args": { + "External id": 1413000,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533303556.126, "dur": 2.137, + "args": { + "External id": 1413001,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533303557.479, "dur": 0.645, + "args": { + "External id": 1413002,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533303559.505, "dur": 17.611, + "args": { + "External id": 1413003,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533303563.838, "dur": 0.695, + "args": { + "External id": 1413004,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533303680.944, "dur": 32.636, + "args": { + "External id": 1413005,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533303735.691, "dur": 16.909, + "args": { + "External id": 1413006,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533303761.309, "dur": 59.642, + "args": { + "External id": 1413007,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533303827.916, "dur": 61.000, + "args": { + "External id": 1413008,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533303913.387, "dur": 28.609, + "args": { + "External id": 1413009,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533303949.150, "dur": 38.480, + "args": { + "External id": 1413010,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533303996.703, "dur": 191.898, + "args": { + "External id": 1413011,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533304206.504, "dur": 59.986, + "args": { + "External id": 1413012,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410533304308.599, "dur": 48.896, + "args": { + "External id": 1413013,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533304392.583, "dur": 57.996, + "args": { + "External id": 1413014,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533304485.489, "dur": 226.084, + "args": { + "External id": 1413015,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533304937.516, "dur": 23.064, + "args": { + "External id": 1413016,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410533304986.868, "dur": 24.708, + "args": { + "External id": 1413017,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305176.089, "dur": 24.157, + "args": { + "External id": 1413018,"Record function id": 0, "Ev Idx": 5529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305181.521, "dur": 17.116, + "args": { + "External id": 1413019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305187.605, "dur": 9.630, + "args": { + "External id": 1413020,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305189.726, "dur": 7.301, + "args": { + "External id": 1413021,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305206.070, "dur": 5.960, + "args": { + "External id": 1413022,"Record function id": 0, "Ev Idx": 5533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305208.080, "dur": 3.354, + "args": { + "External id": 1413023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305209.055, "dur": 1.692, + "args": { + "External id": 1413024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305209.550, "dur": 1.073, + "args": { + "External id": 1413025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305215.794, "dur": 7.823, + "args": { + "External id": 1413026,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305217.298, "dur": 5.790, + "args": { + "External id": 1413027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305217.956, "dur": 4.427, + "args": { + "External id": 1413028,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305218.716, "dur": 3.547, + "args": { + "External id": 1413029,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305227.406, "dur": 4.924, + "args": { + "External id": 1413030,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305228.866, "dur": 2.991, + "args": { + "External id": 1413031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305229.710, "dur": 1.580, + "args": { + "External id": 1413032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305230.124, "dur": 1.057, + "args": { + "External id": 1413033,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305235.841, "dur": 4.765, + "args": { + "External id": 1413034,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305237.488, "dur": 2.688, + "args": { + "External id": 1413035,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305238.302, "dur": 1.415, + "args": { + "External id": 1413036,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305238.739, "dur": 0.852, + "args": { + "External id": 1413037,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305247.848, "dur": 4.598, + "args": { + "External id": 1413038,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305249.291, "dur": 2.680, + "args": { + "External id": 1413039,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305249.823, "dur": 1.564, + "args": { + "External id": 1413040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305250.384, "dur": 0.923, + "args": { + "External id": 1413041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305256.231, "dur": 4.332, + "args": { + "External id": 1413042,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305257.714, "dur": 2.414, + "args": { + "External id": 1413043,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305258.236, "dur": 1.441, + "args": { + "External id": 1413044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305258.835, "dur": 0.752, + "args": { + "External id": 1413045,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305266.799, "dur": 6.491, + "args": { + "External id": 1413046,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305268.900, "dur": 3.643, + "args": { + "External id": 1413047,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305270.001, "dur": 1.910, + "args": { + "External id": 1413048,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305270.701, "dur": 1.041, + "args": { + "External id": 1413049,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305278.707, "dur": 9.459, + "args": { + "External id": 1413050,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533305281.259, "dur": 6.124, + "args": { + "External id": 1413051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305282.403, "dur": 4.260, + "args": { + "External id": 1413052,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533305285.327, "dur": 1.138, + "args": { + "External id": 1413053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533305295.009, "dur": 59212.397, + "args": { + "External id": 1413054,"Record function id": 0, "Sequence number": 15108845, "Fwd thread id": 1, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533305298.270, "dur": 59197.711, + "args": { + "External id": 1413055,"Sequence number": 15108845, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5566 + } + }, + { + "ph": "f", "id": 221, "pid": 2338710, "tid": 2379450, "ts": 6410533305298.270, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410533305347.871, "dur": 57.199, + "args": { + "External id": 1413056,"Record function id": 0, "Ev Idx": 5567 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410533305435.498, "dur": 108.393, + "args": { + "External id": 1413057,"Record function id": 0, "Ev Idx": 5568 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410533305555.301, "dur": 58930.368, + "args": { + "External id": 1413058,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533305691.840, "dur": 11.496, + "args": { + "External id": 1413059,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533305718.004, "dur": 9.259, + "args": { + "External id": 1413060,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533305748.260, "dur": 57732.807, + "args": { + "External id": 1413061,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533305769.549, "dur": 57696.327, + "args": { + "External id": 1413062,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533305872.709, "dur": 23.266, + "args": { + "External id": 1413063,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533305921.195, "dur": 57467.468, + "args": { + "External id": 1413064,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533305924.320, "dur": 57462.831, + "args": { + "External id": 1413065,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533305929.836, "dur": 12.695, + "args": { + "External id": 1413066,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533305945.403, "dur": 57435.901, + "args": { + "External id": 1413067,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533363609.169, "dur": 15.297, + "args": { + "External id": 1413068,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533363613.368, "dur": 10.616, + "args": { + "External id": 1413069,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533363661.678, "dur": 460.055, + "args": { + "External id": 1413070,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533363701.314, "dur": 413.975, + "args": { + "External id": 1413071,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5582, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533363717.769, "dur": 389.692, + "args": { + "External id": 1413072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533364150.439, "dur": 3.134, + "args": { + "External id": 1413073,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5584, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364228.884, "dur": 8.048, + "args": { + "External id": 1413074,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364293.178, "dur": 1.654, + "args": { + "External id": 1413075,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364311.966, "dur": 3.716, + "args": { + "External id": 1413076,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364328.991, "dur": 0.933, + "args": { + "External id": 1413077,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364344.946, "dur": 0.778, + "args": { + "External id": 1413078,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364356.179, "dur": 0.791, + "args": { + "External id": 1413079,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364368.466, "dur": 2.952, + "args": { + "External id": 1413080,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364382.126, "dur": 2.626, + "args": { + "External id": 1413081,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364395.371, "dur": 0.795, + "args": { + "External id": 1413082,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533364528.177, "dur": 2830.789, + "args": { + "External id": 1413083,"Record function id": 0, "Ev Idx": 5594 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410533364553.569, "dur": 591.743, + "args": { + "External id": 1413084,"Record function id": 0, "Ev Idx": 5595 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410533364571.174, "dur": 402.319, + "args": { + "External id": 1413085,"Record function id": 0, "Ev Idx": 5596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364687.858, "dur": 5.049, + "args": { + "External id": 1413086,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364697.035, "dur": 1.158, + "args": { + "External id": 1413087,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364700.218, "dur": 3.295, + "args": { + "External id": 1413088,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364705.720, "dur": 0.891, + "args": { + "External id": 1413089,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364708.637, "dur": 1.065, + "args": { + "External id": 1413090,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364713.697, "dur": 0.863, + "args": { + "External id": 1413091,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364716.700, "dur": 2.562, + "args": { + "External id": 1413092,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364721.251, "dur": 1.106, + "args": { + "External id": 1413093,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364723.955, "dur": 1.169, + "args": { + "External id": 1413094,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533364728.906, "dur": 0.930, + "args": { + "External id": 1413095,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533364750.978, "dur": 180.805, + "args": { + "External id": 1413096,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533364770.278, "dur": 155.961, + "args": { + "External id": 1413097,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533364793.090, "dur": 17.312, + "args": { + "External id": 1413098,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533364814.809, "dur": 79.298, + "args": { + "External id": 1413099,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 5610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533364817.726, "dur": 75.910, + "args": { + "External id": 1413100,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 5611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533364822.136, "dur": 8.629, + "args": { + "External id": 1413101,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533364832.975, "dur": 59.863, + "args": { + "External id": 1413102,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 5613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533365156.193, "dur": 2175.253, + "args": { + "External id": 1413103,"Sequence number": 15108844, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5614 + } + }, + { + "ph": "f", "id": 222, "pid": 2338710, "tid": 2379450, "ts": 6410533365156.193, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533365285.264, "dur": 124.078, + "args": { + "External id": 1413104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533365479.334, "dur": 49.206, + "args": { + "External id": 1413105,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410533365553.501, "dur": 63.376, + "args": { + "External id": 1413106,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533365628.135, "dur": 35.762, + "args": { + "External id": 1413107,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533365673.212, "dur": 35.665, + "args": { + "External id": 1413108,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533365716.807, "dur": 30.656, + "args": { + "External id": 1413109,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533365757.407, "dur": 31.822, + "args": { + "External id": 1413110,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533365822.192, "dur": 27.839, + "args": { + "External id": 1413111,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533365874.977, "dur": 33.810, + "args": { + "External id": 1413112,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533365940.919, "dur": 21.240, + "args": { + "External id": 1413113,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533365978.602, "dur": 15.295, + "args": { + "External id": 1413114,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533366004.624, "dur": 43.200, + "args": { + "External id": 1413115,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533366051.750, "dur": 79.866, + "args": { + "External id": 1413116,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410533366170.410, "dur": 346.031, + "args": { + "External id": 1413117,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533366261.596, "dur": 7.739, + "args": { + "External id": 1413118,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533366271.804, "dur": 4.685, + "args": { + "External id": 1413119,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533366278.233, "dur": 5.350, + "args": { + "External id": 1413120,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533366314.345, "dur": 4.558, + "args": { + "External id": 1413121,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533366365.282, "dur": 6.620, + "args": { + "External id": 1413122,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533366368.576, "dur": 3.156, + "args": { + "External id": 1413123,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533366374.544, "dur": 35.059, + "args": { + "External id": 1413124,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533366381.207, "dur": 1.929, + "args": { + "External id": 1413125,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410533366432.508, "dur": 4.122, + "args": { + "External id": 1413126,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533366435.078, "dur": 1.244, + "args": { + "External id": 1413127,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410533366438.188, "dur": 23.017, + "args": { + "External id": 1413128,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533366443.894, "dur": 0.569, + "args": { + "External id": 1413129,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533366571.524, "dur": 42.265, + "args": { + "External id": 1413130,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533366646.471, "dur": 25.018, + "args": { + "External id": 1413131,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533366690.822, "dur": 75.193, + "args": { + "External id": 1413132,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533366776.640, "dur": 48.215, + "args": { + "External id": 1413133,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533366837.627, "dur": 23.480, + "args": { + "External id": 1413134,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533366867.800, "dur": 33.464, + "args": { + "External id": 1413135,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533366909.025, "dur": 29.678, + "args": { + "External id": 1413136,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410533366947.184, "dur": 31.814, + "args": { + "External id": 1413137,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410533367012.497, "dur": 82.394, + "args": { + "External id": 1413138,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533367136.869, "dur": 36.718, + "args": { + "External id": 1413139,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533367193.278, "dur": 20.593, + "args": { + "External id": 1413140,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410533367242.430, "dur": 16.338, + "args": { + "External id": 1413141,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410533367274.110, "dur": 17.882, + "args": { + "External id": 1413142,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367384.804, "dur": 18.239, + "args": { + "External id": 1413143,"Record function id": 0, "Ev Idx": 5654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367389.076, "dur": 12.787, + "args": { + "External id": 1413144,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367394.185, "dur": 6.527, + "args": { + "External id": 1413145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367395.872, "dur": 4.736, + "args": { + "External id": 1413146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367407.636, "dur": 26.120, + "args": { + "External id": 1413147,"Record function id": 0, "Ev Idx": 5658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367409.374, "dur": 22.994, + "args": { + "External id": 1413148,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367410.355, "dur": 20.793, + "args": { + "External id": 1413149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367411.053, "dur": 19.556, + "args": { + "External id": 1413150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367440.745, "dur": 7.157, + "args": { + "External id": 1413151,"Record function id": 0, "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367443.007, "dur": 4.365, + "args": { + "External id": 1413152,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367444.358, "dur": 2.445, + "args": { + "External id": 1413153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367445.602, "dur": 1.106, + "args": { + "External id": 1413154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367451.932, "dur": 5.571, + "args": { + "External id": 1413155,"Record function id": 0, "Ev Idx": 5666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367453.952, "dur": 3.029, + "args": { + "External id": 1413156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367454.883, "dur": 1.615, + "args": { + "External id": 1413157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367455.550, "dur": 0.868, + "args": { + "External id": 1413158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367461.348, "dur": 5.855, + "args": { + "External id": 1413159,"Record function id": 0, "Ev Idx": 5670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367463.752, "dur": 2.932, + "args": { + "External id": 1413160,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367464.767, "dur": 1.430, + "args": { + "External id": 1413161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367465.132, "dur": 0.984, + "args": { + "External id": 1413162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367470.985, "dur": 7.327, + "args": { + "External id": 1413163,"Record function id": 0, "Ev Idx": 5674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367472.993, "dur": 4.778, + "args": { + "External id": 1413164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367473.861, "dur": 3.416, + "args": { + "External id": 1413165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367476.497, "dur": 0.705, + "args": { + "External id": 1413166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367482.447, "dur": 5.380, + "args": { + "External id": 1413167,"Record function id": 0, "Ev Idx": 5678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367484.300, "dur": 3.023, + "args": { + "External id": 1413168,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367485.427, "dur": 1.385, + "args": { + "External id": 1413169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367485.978, "dur": 0.754, + "args": { + "External id": 1413170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367492.132, "dur": 5.260, + "args": { + "External id": 1413171,"Record function id": 0, "Ev Idx": 5682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367494.087, "dur": 2.780, + "args": { + "External id": 1413172,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367494.782, "dur": 1.591, + "args": { + "External id": 1413173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367495.450, "dur": 0.845, + "args": { + "External id": 1413174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367501.466, "dur": 7.346, + "args": { + "External id": 1413175,"Record function id": 0, "Ev Idx": 5686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533367503.413, "dur": 4.862, + "args": { + "External id": 1413176,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367504.333, "dur": 3.464, + "args": { + "External id": 1413177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533367504.708, "dur": 3.009, + "args": { + "External id": 1413178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533367514.003, "dur": 61092.408, + "args": { + "External id": 1413179,"Record function id": 0, "Sequence number": 15108843, "Fwd thread id": 1, "Ev Idx": 5690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533367516.432, "dur": 61079.340, + "args": { + "External id": 1413180,"Sequence number": 15108843, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5691 + } + }, + { + "ph": "f", "id": 223, "pid": 2338710, "tid": 2379450, "ts": 6410533367516.432, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410533367554.400, "dur": 48.905, + "args": { + "External id": 1413181,"Record function id": 0, "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410533367613.353, "dur": 84.774, + "args": { + "External id": 1413182,"Record function id": 0, "Ev Idx": 5693 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410533367705.421, "dur": 60880.314, + "args": { + "External id": 1413183,"Record function id": 0, "Ev Idx": 5694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533367815.123, "dur": 9.357, + "args": { + "External id": 1413184,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533367835.674, "dur": 6.019, + "args": { + "External id": 1413185,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533367857.675, "dur": 59696.501, + "args": { + "External id": 1413186,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533367874.558, "dur": 59663.904, + "args": { + "External id": 1413187,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533367976.816, "dur": 20.714, + "args": { + "External id": 1413188,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533368021.139, "dur": 59457.778, + "args": { + "External id": 1413189,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533368029.029, "dur": 59448.489, + "args": { + "External id": 1413190,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533368034.539, "dur": 10.355, + "args": { + "External id": 1413191,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533368047.470, "dur": 59422.356, + "args": { + "External id": 1413192,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533427685.077, "dur": 15.281, + "args": { + "External id": 1413193,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533427689.543, "dur": 10.315, + "args": { + "External id": 1413194,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533427738.732, "dur": 472.636, + "args": { + "External id": 1413195,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533427777.482, "dur": 427.451, + "args": { + "External id": 1413196,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5707, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533427792.258, "dur": 405.568, + "args": { + "External id": 1413197,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533428242.227, "dur": 2.816, + "args": { + "External id": 1413198,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5709, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428317.631, "dur": 8.160, + "args": { + "External id": 1413199,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428378.891, "dur": 4.253, + "args": { + "External id": 1413200,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428402.611, "dur": 1.367, + "args": { + "External id": 1413201,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428440.191, "dur": 1.767, + "args": { + "External id": 1413202,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428457.101, "dur": 0.856, + "args": { + "External id": 1413203,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428470.018, "dur": 2.719, + "args": { + "External id": 1413204,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428484.092, "dur": 0.859, + "args": { + "External id": 1413205,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428499.036, "dur": 1.986, + "args": { + "External id": 1413206,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533428512.387, "dur": 0.709, + "args": { + "External id": 1413207,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533428625.944, "dur": 330.155, + "args": { + "External id": 1413208,"Record function id": 0, "Sequence number": 15108842, "Fwd thread id": 1, "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410533428629.359, "dur": 315.564, + "args": { + "External id": 1413209,"Sequence number": 15108842, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5720 + } + }, + { + "ph": "f", "id": 224, "pid": 2338710, "tid": 2379450, "ts": 6410533428629.359, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 2338710, "tid": 2379450, + "ts": 6410533428775.054, "dur": 57.167, + "args": { + "External id": 1413210,"kernel_hash": "ci46ycwqu4mevlefaywvsre33v5ki6y5q5evkfmt4t2fie5todnp", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/i4/ci46ycwqu4mevlefaywvsre33v5ki6y5q5evkfmt4t2fie5todnp.py", "kernel_backend": "triton", "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 5721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_1", "pid": 2338710, "tid": 2379450, + "ts": 6410533428851.138, "dur": 29.865, + "args": { + "External id": 1413211,"kernel_hash": "c4hfnruzhc7gtb7rldzmrokxpon7tcgieufpcwt6pxhd3syqv6zy", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/4h/c4hfnruzhc7gtb7rldzmrokxpon7tcgieufpcwt6pxhd3syqv6zy.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096, 4096], [32000, 4096], []], "Ev Idx": 5722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_2", "pid": 2338710, "tid": 2379450, + "ts": 6410533428904.195, "dur": 22.856, + "args": { + "External id": 1413212,"kernel_hash": "cagfbb4snc4nnt5qtlfe5j5npoahg3qjke5pbuljm6ouabijdwft", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/ag/cagfbb4snc4nnt5qtlfe5j5npoahg3qjke5pbuljm6ouabijdwft.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 5723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533428967.807, "dur": 16.067, + "args": { + "External id": 1413213,"Record function id": 0, "Ev Idx": 5724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410533428972.078, "dur": 10.848, + "args": { + "External id": 1413214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 5725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533428976.053, "dur": 5.973, + "args": { + "External id": 1413215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 5726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410533428977.470, "dur": 4.429, + "args": { + "External id": 1413216,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 5727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_post_backward_callback", "pid": 2338710, "tid": 2379450, + "ts": 6410533429009.765, "dur": 12661.871, + "args": { + "External id": 1413217,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 2338710, "tid": 2379450, + "ts": 6410533429034.487, "dur": 102.911, + "args": { + "External id": 1413218,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 2338710, "tid": 2379450, + "ts": 6410533429146.741, "dur": 344.168, + "args": { + "External id": 1413219,"Record function id": 0, "Ev Idx": 5730 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 2338710, "tid": 2379450, + "ts": 6410533429500.407, "dur": 11855.035, + "args": { + "External id": 1413220,"Record function id": 0, "Ev Idx": 5731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533429659.054, "dur": 9.319, + "args": { + "External id": 1413221,"Record function id": 0, "Concrete Inputs": ["[1134596096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410533429682.527, "dur": 6.019, + "args": { + "External id": 1413222,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1134596096], []], "Ev Idx": 5733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533429713.223, "dur": 10246.214, + "args": { + "External id": 1413223,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [141824512, 1]], "Input Dims": [[], [], [], [8, 141824512]], "Ev Idx": 5734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410533429734.935, "dur": 10207.778, + "args": { + "External id": 1413224,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [141824512, 1]], "Input Dims": [[], [], [], [8, 141824512]], "Ev Idx": 5735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533430697.520, "dur": 31.976, + "args": { + "External id": 1413225,"Record function id": 0, "Concrete Inputs": ["[277237]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410533431094.578, "dur": 8779.443, + "args": { + "External id": 1413226,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[277237], [], [], [], [], [], [], []], "Ev Idx": 5737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410533431101.058, "dur": 8771.360, + "args": { + "External id": 1413227,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[277237], [], [], [], [], [], []], "Ev Idx": 5738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533431109.654, "dur": 31.023, + "args": { + "External id": 1413228,"Record function id": 0, "Concrete Inputs": ["[277237]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410533431149.016, "dur": 8714.863, + "args": { + "External id": 1413229,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[277237], [277237], []], "Ev Idx": 5740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533440177.407, "dur": 15.698, + "args": { + "External id": 1413230,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1134596096], [], [], [], [], []], "Ev Idx": 5741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410533440181.732, "dur": 10.561, + "args": { + "External id": 1413231,"Record function id": 0, "Concrete Inputs": ["[141824512]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410533440228.933, "dur": 315.911, + "args": { + "External id": 1413232,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[141824512], [1134596096], [], [], [], []], "Ev Idx": 5743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533440264.890, "dur": 274.235, + "args": { + "External id": 1413233,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 141824512, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1134596096], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5744, "In msg nelems": 1134596096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410533440280.377, "dur": 251.929, + "args": { + "External id": 1413234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1134596096]], "Ev Idx": 5745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410533440570.061, "dur": 2.634, + "args": { + "External id": 1413235,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5746, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440640.359, "dur": 9.723, + "args": { + "External id": 1413236,"Record function id": 0, "Concrete Inputs": ["", "[4000, 4096]", "[4096, 1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440701.894, "dur": 1.604, + "args": { + "External id": 1413237,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440721.182, "dur": 1.264, + "args": { + "External id": 1413238,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "16384512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440738.495, "dur": 1.003, + "args": { + "External id": 1413239,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "18481664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440754.075, "dur": 3.360, + "args": { + "External id": 1413240,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "19005952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440768.768, "dur": 1.218, + "args": { + "External id": 1413241,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "19530240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440781.850, "dur": 2.331, + "args": { + "External id": 1413242,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440796.209, "dur": 0.734, + "args": { + "External id": 1413243,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "21627904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440808.748, "dur": 3.935, + "args": { + "External id": 1413244,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "28967936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440825.902, "dur": 0.725, + "args": { + "External id": 1413245,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "36307968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440838.685, "dur": 0.827, + "args": { + "External id": 1413246,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440852.450, "dur": 0.917, + "args": { + "External id": 1413247,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "43648512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440864.552, "dur": 3.036, + "args": { + "External id": 1413248,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "45745664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440878.607, "dur": 0.865, + "args": { + "External id": 1413249,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "46269952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440892.808, "dur": 2.023, + "args": { + "External id": 1413250,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "46794240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440906.835, "dur": 0.682, + "args": { + "External id": 1413251,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440918.542, "dur": 2.987, + "args": { + "External id": 1413252,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "48891904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440933.355, "dur": 0.706, + "args": { + "External id": 1413253,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "56231936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440945.717, "dur": 0.729, + "args": { + "External id": 1413254,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "63571968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440959.090, "dur": 0.629, + "args": { + "External id": 1413255,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440972.958, "dur": 5.608, + "args": { + "External id": 1413256,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "70912512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533440989.216, "dur": 1.073, + "args": { + "External id": 1413257,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "73009664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441001.250, "dur": 1.369, + "args": { + "External id": 1413258,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "73533952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441024.935, "dur": 1.078, + "args": { + "External id": 1413259,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "74058240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441038.435, "dur": 3.105, + "args": { + "External id": 1413260,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441092.612, "dur": 2.131, + "args": { + "External id": 1413261,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "76155904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441112.256, "dur": 1.264, + "args": { + "External id": 1413262,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "83495936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441125.252, "dur": 1.118, + "args": { + "External id": 1413263,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "90835968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441137.662, "dur": 4.100, + "args": { + "External id": 1413264,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441152.854, "dur": 1.349, + "args": { + "External id": 1413265,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "98176512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441168.931, "dur": 1.098, + "args": { + "External id": 1413266,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "100273664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441180.544, "dur": 1.149, + "args": { + "External id": 1413267,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "100797952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441192.677, "dur": 3.550, + "args": { + "External id": 1413268,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "101322240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441206.665, "dur": 1.055, + "args": { + "External id": 1413269,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441218.517, "dur": 2.547, + "args": { + "External id": 1413270,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "103419904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441234.906, "dur": 1.047, + "args": { + "External id": 1413271,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "110759936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441247.361, "dur": 3.833, + "args": { + "External id": 1413272,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "118099968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441262.175, "dur": 0.989, + "args": { + "External id": 1413273,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410533441274.891, "dur": 1.218, + "args": { + "External id": 1413274,"Record function id": 0, "Concrete Inputs": ["", "[4000, 4096]", "[4096, 1]", "125440512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534578147.591, "dur": 122.406, + "args": { + "External id": 1413275,"Record function id": 0, "Sequence number": 15109297, "Fwd thread id": 1, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534578158.201, "dur": 101.150, + "args": { + "External id": 1413276,"Sequence number": 15109297, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5787 + } + }, + { + "ph": "f", "id": 225, "pid": 2338710, "tid": 2379450, "ts": 6410534578158.201, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338710, "tid": 2379450, + "ts": 6410534578167.371, "dur": 90.370, + "args": { + "External id": 1413277,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534578280.221, "dur": 311.257, + "args": { + "External id": 1413278,"Record function id": 0, "Ev Idx": 5789 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534578369.546, "dur": 132.910, + "args": { + "External id": 1413279,"Record function id": 0, "Ev Idx": 5790 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.25", "pid": 2338710, "tid": 2379450, + "ts": 6410534578407.128, "dur": 80.322, + "args": { + "External id": 1413280,"Record function id": 0, "Ev Idx": 5791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534578509.469, "dur": 2.695, + "args": { + "External id": 1413281,"Sequence number": 15109296, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5792 + } + }, + { + "ph": "f", "id": 226, "pid": 2338710, "tid": 2379450, "ts": 6410534578509.469, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534578517.836, "dur": 66.397, + "args": { + "External id": 1413282,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534578527.057, "dur": 56.177, + "args": { + "External id": 1413283,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 5794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534578540.299, "dur": 3.017, + "args": { + "External id": 1413284,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 5795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534578604.356, "dur": 39775.159, + "args": { + "External id": 1413285,"Record function id": 0, "Sequence number": 15109294, "Fwd thread id": 1, "Ev Idx": 5796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534578606.843, "dur": 39754.617, + "args": { + "External id": 1413286,"Sequence number": 15109294, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5797 + } + }, + { + "ph": "f", "id": 227, "pid": 2338710, "tid": 2379450, "ts": 6410534578606.843, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534578658.843, "dur": 4.629, + "args": { + "External id": 1413287,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534578667.161, "dur": 39297.705, + "args": { + "External id": 1413288,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534578669.636, "dur": 39294.703, + "args": { + "External id": 1413289,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534578674.144, "dur": 9.821, + "args": { + "External id": 1413290,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534578686.003, "dur": 39276.159, + "args": { + "External id": 1413291,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338710, "tid": 2379450, + "ts": 6410534617972.545, "dur": 0.831, + "args": { + "External id": 1413292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410534617976.049, "dur": 5.978, + "args": { + "External id": 1413293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410534617980.156, "dur": 1.620, + "args": { + "External id": 1413294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2379450, + "ts": 6410534617990.909, "dur": 38.788, + "args": { + "External id": 1413295,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 5806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2379450, + "ts": 6410534618040.255, "dur": 87.343, + "args": { + "External id": 1413296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2379450, + "ts": 6410534618042.600, "dur": 84.710, + "args": { + "External id": 1413297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2379450, + "ts": 6410534618044.936, "dur": 81.589, + "args": { + "External id": 1413298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618397.428, "dur": 41.304, + "args": { + "External id": 1413299,"Record function id": 0, "Sequence number": 15109293, "Fwd thread id": 1, "Ev Idx": 5810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618399.960, "dur": 33.156, + "args": { + "External id": 1413300,"Sequence number": 15109293, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 5811 + } + }, + { + "ph": "f", "id": 228, "pid": 2338710, "tid": 2379450, "ts": 6410534618399.960, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534618406.386, "dur": 26.406, + "args": { + "External id": 1413301,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534618410.911, "dur": 21.292, + "args": { + "External id": 1413302,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618446.379, "dur": 142.104, + "args": { + "External id": 1413303,"Record function id": 0, "Sequence number": 15109292, "Fwd thread id": 1, "Ev Idx": 5814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618448.123, "dur": 130.352, + "args": { + "External id": 1413304,"Sequence number": 15109292, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5815 + } + }, + { + "ph": "f", "id": 229, "pid": 2338710, "tid": 2379450, "ts": 6410534618448.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534618452.670, "dur": 125.161, + "args": { + "External id": 1413305,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 5816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534618460.182, "dur": 49.256, + "args": { + "External id": 1413306,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534618464.162, "dur": 9.350, + "args": { + "External id": 1413307,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618476.000, "dur": 33.028, + "args": { + "External id": 1413308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618481.223, "dur": 27.253, + "args": { + "External id": 1413309,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534618512.048, "dur": 7.114, + "args": { + "External id": 1413310,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534618516.519, "dur": 1.954, + "args": { + "External id": 1413311,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618522.784, "dur": 53.946, + "args": { + "External id": 1413312,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618594.996, "dur": 76.934, + "args": { + "External id": 1413313,"Record function id": 0, "Sequence number": 15109291, "Fwd thread id": 1, "Ev Idx": 5824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618596.522, "dur": 70.994, + "args": { + "External id": 1413314,"Sequence number": 15109291, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5825 + } + }, + { + "ph": "f", "id": 230, "pid": 2338710, "tid": 2379450, "ts": 6410534618596.522, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534618600.102, "dur": 67.059, + "args": { + "External id": 1413315,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "3"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534618604.070, "dur": 24.167, + "args": { + "External id": 1413316,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534618605.717, "dur": 3.620, + "args": { + "External id": 1413317,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618610.254, "dur": 17.682, + "args": { + "External id": 1413318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618613.189, "dur": 14.215, + "args": { + "External id": 1413319,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410534618630.243, "dur": 10.272, + "args": { + "External id": 1413320,"Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 5831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534618638.159, "dur": 1.475, + "args": { + "External id": 1413321,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618641.754, "dur": 24.695, + "args": { + "External id": 1413322,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618676.614, "dur": 230.984, + "args": { + "External id": 1413323,"Record function id": 0, "Sequence number": 15109290, "Fwd thread id": 1, "Ev Idx": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618677.901, "dur": 224.556, + "args": { + "External id": 1413324,"Sequence number": 15109290, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5835 + } + }, + { + "ph": "f", "id": 231, "pid": 2338710, "tid": 2379450, "ts": 6410534618677.901, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534618680.490, "dur": 221.419, + "args": { + "External id": 1413325,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534618682.266, "dur": 22.890, + "args": { + "External id": 1413326,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534618683.906, "dur": 3.952, + "args": { + "External id": 1413327,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618688.609, "dur": 16.235, + "args": { + "External id": 1413328,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618690.179, "dur": 14.228, + "args": { + "External id": 1413329,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534618706.733, "dur": 3.891, + "args": { + "External id": 1413330,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534618709.075, "dur": 1.221, + "args": { + "External id": 1413331,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618711.611, "dur": 188.860, + "args": { + "External id": 1413332,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618913.587, "dur": 110.305, + "args": { + "External id": 1413333,"Record function id": 0, "Sequence number": 15109289, "Fwd thread id": 1, "Ev Idx": 5844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534618917.385, "dur": 100.519, + "args": { + "External id": 1413334,"Sequence number": 15109289, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5845 + } + }, + { + "ph": "f", "id": 232, "pid": 2338710, "tid": 2379450, "ts": 6410534618917.385, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534618920.126, "dur": 97.334, + "args": { + "External id": 1413335,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534618921.698, "dur": 20.737, + "args": { + "External id": 1413336,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534618923.426, "dur": 2.665, + "args": { + "External id": 1413337,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618926.744, "dur": 15.322, + "args": { + "External id": 1413338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618928.630, "dur": 12.775, + "args": { + "External id": 1413339,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534618943.438, "dur": 6.838, + "args": { + "External id": 1413340,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534618946.209, "dur": 3.775, + "args": { + "External id": 1413341,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534618958.251, "dur": 58.325, + "args": { + "External id": 1413342,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534619029.931, "dur": 87.633, + "args": { + "External id": 1413343,"Record function id": 0, "Sequence number": 15109288, "Fwd thread id": 1, "Ev Idx": 5854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534619031.746, "dur": 1.310, + "args": { + "External id": 1413344,"Sequence number": 15109288, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5855 + } + }, + { + "ph": "f", "id": 233, "pid": 2338710, "tid": 2379450, "ts": 6410534619031.746, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534619036.737, "dur": 75.258, + "args": { + "External id": 1413345,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534619042.471, "dur": 68.520, + "args": { + "External id": 1413346,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 5857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534619050.652, "dur": 0.663, + "args": { + "External id": 1413347,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 5858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534619127.181, "dur": 2416.342, + "args": { + "External id": 1413348,"Record function id": 0, "Sequence number": 15109286, "Fwd thread id": 1, "Ev Idx": 5859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534619129.504, "dur": 2358.795, + "args": { + "External id": 1413349,"Sequence number": 15109286, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5860 + } + }, + { + "ph": "f", "id": 234, "pid": 2338710, "tid": 2379450, "ts": 6410534619129.504, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534619179.288, "dur": 5.148, + "args": { + "External id": 1413350,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534619187.605, "dur": 1974.757, + "args": { + "External id": 1413351,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534619190.085, "dur": 1971.828, + "args": { + "External id": 1413352,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534619194.442, "dur": 8.017, + "args": { + "External id": 1413353,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534619203.755, "dur": 1956.552, + "args": { + "External id": 1413354,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338710, "tid": 2379450, + "ts": 6410534621168.227, "dur": 0.595, + "args": { + "External id": 1413355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621171.108, "dur": 4.045, + "args": { + "External id": 1413356,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621173.658, "dur": 1.259, + "args": { + "External id": 1413357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2379450, + "ts": 6410534621182.311, "dur": 37.331, + "args": { + "External id": 1413358,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 5869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2379450, + "ts": 6410534621228.467, "dur": 63.348, + "args": { + "External id": 1413359,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2379450, + "ts": 6410534621232.958, "dur": 58.479, + "args": { + "External id": 1413360,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2379450, + "ts": 6410534621235.388, "dur": 55.376, + "args": { + "External id": 1413361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621510.951, "dur": 26.681, + "args": { + "External id": 1413362,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 5873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621560.174, "dur": 20.430, + "args": { + "External id": 1413363,"Record function id": 0, "Sequence number": 15109285, "Fwd thread id": 1, "Ev Idx": 5874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621562.528, "dur": 15.018, + "args": { + "External id": 1413364,"Sequence number": 15109285, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 5875 + } + }, + { + "ph": "f", "id": 235, "pid": 2338710, "tid": 2379450, "ts": 6410534621562.528, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534621568.579, "dur": 8.677, + "args": { + "External id": 1413365,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534621571.143, "dur": 5.782, + "args": { + "External id": 1413366,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621585.067, "dur": 103.895, + "args": { + "External id": 1413367,"Record function id": 0, "Sequence number": 15109284, "Fwd thread id": 1, "Ev Idx": 5878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621586.403, "dur": 95.865, + "args": { + "External id": 1413368,"Sequence number": 15109284, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5879 + } + }, + { + "ph": "f", "id": 236, "pid": 2338710, "tid": 2379450, "ts": 6410534621586.403, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534621589.887, "dur": 91.804, + "args": { + "External id": 1413369,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 5880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534621594.031, "dur": 30.768, + "args": { + "External id": 1413370,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534621596.518, "dur": 5.537, + "args": { + "External id": 1413371,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621603.652, "dur": 20.824, + "args": { + "External id": 1413372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621606.809, "dur": 17.173, + "args": { + "External id": 1413373,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 5884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534621629.198, "dur": 6.056, + "args": { + "External id": 1413374,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 5885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534621632.968, "dur": 1.771, + "args": { + "External id": 1413375,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621636.783, "dur": 43.855, + "args": { + "External id": 1413376,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621694.121, "dur": 72.179, + "args": { + "External id": 1413377,"Record function id": 0, "Sequence number": 15109283, "Fwd thread id": 1, "Ev Idx": 5888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621695.235, "dur": 66.637, + "args": { + "External id": 1413378,"Sequence number": 15109283, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5889 + } + }, + { + "ph": "f", "id": 237, "pid": 2338710, "tid": 2379450, "ts": 6410534621695.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534621698.385, "dur": 62.927, + "args": { + "External id": 1413379,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "2"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534621700.897, "dur": 19.533, + "args": { + "External id": 1413380,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534621702.186, "dur": 2.934, + "args": { + "External id": 1413381,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621705.975, "dur": 14.161, + "args": { + "External id": 1413382,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621707.029, "dur": 12.598, + "args": { + "External id": 1413383,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410534621727.753, "dur": 9.669, + "args": { + "External id": 1413384,"Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 5895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534621735.596, "dur": 1.088, + "args": { + "External id": 1413385,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621738.151, "dur": 22.429, + "args": { + "External id": 1413386,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621770.962, "dur": 156.689, + "args": { + "External id": 1413387,"Record function id": 0, "Sequence number": 15109282, "Fwd thread id": 1, "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621772.087, "dur": 149.218, + "args": { + "External id": 1413388,"Sequence number": 15109282, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5899 + } + }, + { + "ph": "f", "id": 238, "pid": 2338710, "tid": 2379450, "ts": 6410534621772.087, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534621774.246, "dur": 146.542, + "args": { + "External id": 1413389,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534621775.765, "dur": 23.536, + "args": { + "External id": 1413390,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534621776.990, "dur": 2.778, + "args": { + "External id": 1413391,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621780.390, "dur": 18.624, + "args": { + "External id": 1413392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621781.310, "dur": 17.131, + "args": { + "External id": 1413393,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534621800.626, "dur": 6.426, + "args": { + "External id": 1413394,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534621803.368, "dur": 3.342, + "args": { + "External id": 1413395,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621810.024, "dur": 109.592, + "args": { + "External id": 1413396,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621934.430, "dur": 180.298, + "args": { + "External id": 1413397,"Record function id": 0, "Sequence number": 15109281, "Fwd thread id": 1, "Ev Idx": 5908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534621935.757, "dur": 111.253, + "args": { + "External id": 1413398,"Sequence number": 15109281, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5909 + } + }, + { + "ph": "f", "id": 239, "pid": 2338710, "tid": 2379450, "ts": 6410534621935.757, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534621938.330, "dur": 108.249, + "args": { + "External id": 1413399,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534621940.017, "dur": 21.057, + "args": { + "External id": 1413400,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534621941.720, "dur": 2.620, + "args": { + "External id": 1413401,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621945.310, "dur": 15.453, + "args": { + "External id": 1413402,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621946.803, "dur": 13.473, + "args": { + "External id": 1413403,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534621962.085, "dur": 3.225, + "args": { + "External id": 1413404,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534621964.269, "dur": 0.798, + "args": { + "External id": 1413405,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534621969.262, "dur": 76.405, + "args": { + "External id": 1413406,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534622089.790, "dur": 22.446, + "args": { + "External id": 1413407,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534622123.164, "dur": 46.786, + "args": { + "External id": 1413408,"Record function id": 0, "Sequence number": 15109280, "Fwd thread id": 1, "Ev Idx": 5919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534622124.785, "dur": 1.456, + "args": { + "External id": 1413409,"Sequence number": 15109280, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5920 + } + }, + { + "ph": "f", "id": 240, "pid": 2338710, "tid": 2379450, "ts": 6410534622124.785, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534622129.900, "dur": 34.382, + "args": { + "External id": 1413410,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534622133.056, "dur": 30.683, + "args": { + "External id": 1413411,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 5922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534622140.553, "dur": 0.864, + "args": { + "External id": 1413412,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 5923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534622176.025, "dur": 3356.805, + "args": { + "External id": 1413413,"Record function id": 0, "Sequence number": 15109278, "Fwd thread id": 1, "Ev Idx": 5924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534622177.815, "dur": 3310.002, + "args": { + "External id": 1413414,"Sequence number": 15109278, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5925 + } + }, + { + "ph": "f", "id": 241, "pid": 2338710, "tid": 2379450, "ts": 6410534622177.815, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534622221.707, "dur": 3.290, + "args": { + "External id": 1413415,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534622228.004, "dur": 2985.224, + "args": { + "External id": 1413416,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534622229.910, "dur": 2983.029, + "args": { + "External id": 1413417,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534622233.754, "dur": 5.350, + "args": { + "External id": 1413418,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534622240.451, "dur": 2970.897, + "args": { + "External id": 1413419,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338710, "tid": 2379450, + "ts": 6410534625217.488, "dur": 0.324, + "args": { + "External id": 1413420,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625219.182, "dur": 5.490, + "args": { + "External id": 1413421,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625223.319, "dur": 1.162, + "args": { + "External id": 1413422,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2379450, + "ts": 6410534625230.446, "dur": 27.557, + "args": { + "External id": 1413423,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2379450, + "ts": 6410534625264.541, "dur": 46.984, + "args": { + "External id": 1413424,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2379450, + "ts": 6410534625266.327, "dur": 44.878, + "args": { + "External id": 1413425,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2379450, + "ts": 6410534625268.088, "dur": 42.720, + "args": { + "External id": 1413426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625504.887, "dur": 22.376, + "args": { + "External id": 1413427,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 5938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625545.957, "dur": 17.072, + "args": { + "External id": 1413428,"Record function id": 0, "Sequence number": 15109277, "Fwd thread id": 1, "Ev Idx": 5939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625547.649, "dur": 11.700, + "args": { + "External id": 1413429,"Sequence number": 15109277, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 5940 + } + }, + { + "ph": "f", "id": 242, "pid": 2338710, "tid": 2379450, "ts": 6410534625547.649, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534625552.141, "dur": 6.864, + "args": { + "External id": 1413430,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534625553.910, "dur": 4.853, + "args": { + "External id": 1413431,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625567.124, "dur": 91.049, + "args": { + "External id": 1413432,"Record function id": 0, "Sequence number": 15109276, "Fwd thread id": 1, "Ev Idx": 5943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625568.426, "dur": 83.620, + "args": { + "External id": 1413433,"Sequence number": 15109276, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5944 + } + }, + { + "ph": "f", "id": 243, "pid": 2338710, "tid": 2379450, "ts": 6410534625568.426, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534625570.864, "dur": 80.568, + "args": { + "External id": 1413434,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 5945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534625574.768, "dur": 30.635, + "args": { + "External id": 1413435,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534625579.600, "dur": 3.963, + "args": { + "External id": 1413436,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625584.739, "dur": 20.321, + "args": { + "External id": 1413437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625587.032, "dur": 17.552, + "args": { + "External id": 1413438,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 5949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534625607.427, "dur": 8.221, + "args": { + "External id": 1413439,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 5950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534625611.536, "dur": 3.659, + "args": { + "External id": 1413440,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625617.196, "dur": 33.109, + "args": { + "External id": 1413441,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625663.374, "dur": 63.673, + "args": { + "External id": 1413442,"Record function id": 0, "Sequence number": 15109275, "Fwd thread id": 1, "Ev Idx": 5953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625664.532, "dur": 58.306, + "args": { + "External id": 1413443,"Sequence number": 15109275, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5954 + } + }, + { + "ph": "f", "id": 244, "pid": 2338710, "tid": 2379450, "ts": 6410534625664.532, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534625667.232, "dur": 55.122, + "args": { + "External id": 1413444,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534625669.687, "dur": 24.718, + "args": { + "External id": 1413445,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534625671.657, "dur": 2.905, + "args": { + "External id": 1413446,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625675.640, "dur": 18.442, + "args": { + "External id": 1413447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625679.034, "dur": 14.410, + "args": { + "External id": 1413448,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410534625695.957, "dur": 6.715, + "args": { + "External id": 1413449,"Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 5960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534625700.813, "dur": 1.153, + "args": { + "External id": 1413450,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625703.816, "dur": 17.995, + "args": { + "External id": 1413451,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625731.420, "dur": 133.794, + "args": { + "External id": 1413452,"Record function id": 0, "Sequence number": 15109274, "Fwd thread id": 1, "Ev Idx": 5963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625732.713, "dur": 127.399, + "args": { + "External id": 1413453,"Sequence number": 15109274, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5964 + } + }, + { + "ph": "f", "id": 245, "pid": 2338710, "tid": 2379450, "ts": 6410534625732.713, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534625734.937, "dur": 124.705, + "args": { + "External id": 1413454,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534625736.488, "dur": 22.564, + "args": { + "External id": 1413455,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534625737.798, "dur": 2.705, + "args": { + "External id": 1413456,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625741.524, "dur": 17.187, + "args": { + "External id": 1413457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625742.377, "dur": 15.841, + "args": { + "External id": 1413458,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534625762.679, "dur": 3.435, + "args": { + "External id": 1413459,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534625765.174, "dur": 0.610, + "args": { + "External id": 1413460,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625766.863, "dur": 91.541, + "args": { + "External id": 1413461,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625871.018, "dur": 117.114, + "args": { + "External id": 1413462,"Record function id": 0, "Sequence number": 15109273, "Fwd thread id": 1, "Ev Idx": 5973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625872.557, "dur": 93.404, + "args": { + "External id": 1413463,"Sequence number": 15109273, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5974 + } + }, + { + "ph": "f", "id": 246, "pid": 2338710, "tid": 2379450, "ts": 6410534625872.557, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534625874.282, "dur": 91.061, + "args": { + "External id": 1413464,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534625876.251, "dur": 21.873, + "args": { + "External id": 1413465,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534625877.588, "dur": 2.523, + "args": { + "External id": 1413466,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625881.077, "dur": 16.711, + "args": { + "External id": 1413467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625881.886, "dur": 15.502, + "args": { + "External id": 1413468,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534625899.364, "dur": 3.447, + "args": { + "External id": 1413469,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534625901.884, "dur": 0.672, + "args": { + "External id": 1413470,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625905.841, "dur": 58.622, + "args": { + "External id": 1413471,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534625970.812, "dur": 15.742, + "args": { + "External id": 1413472,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625993.925, "dur": 45.172, + "args": { + "External id": 1413473,"Record function id": 0, "Sequence number": 15109272, "Fwd thread id": 1, "Ev Idx": 5984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534625995.511, "dur": 1.390, + "args": { + "External id": 1413474,"Sequence number": 15109272, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5985 + } + }, + { + "ph": "f", "id": 247, "pid": 2338710, "tid": 2379450, "ts": 6410534625995.511, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534625999.464, "dur": 34.320, + "args": { + "External id": 1413475,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534626001.989, "dur": 31.284, + "args": { + "External id": 1413476,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 5987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534626008.318, "dur": 2.955, + "args": { + "External id": 1413477,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 5988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534626045.019, "dur": 3462.757, + "args": { + "External id": 1413478,"Record function id": 0, "Sequence number": 15109271, "Fwd thread id": 1, "Ev Idx": 5989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534626093.978, "dur": 3370.812, + "args": { + "External id": 1413479,"Sequence number": 15109271, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5990 + } + }, + { + "ph": "f", "id": 248, "pid": 2338710, "tid": 2379450, "ts": 6410534626093.978, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534626131.775, "dur": 3.418, + "args": { + "External id": 1413480,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534626138.249, "dur": 3072.339, + "args": { + "External id": 1413481,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534626140.096, "dur": 3070.155, + "args": { + "External id": 1413482,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534626143.878, "dur": 5.156, + "args": { + "External id": 1413483,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534626150.440, "dur": 3058.540, + "args": { + "External id": 1413484,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338710, "tid": 2379450, + "ts": 6410534629215.113, "dur": 0.427, + "args": { + "External id": 1413485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629217.136, "dur": 5.469, + "args": { + "External id": 1413486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629221.442, "dur": 0.974, + "args": { + "External id": 1413487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2379450, + "ts": 6410534629227.904, "dur": 26.782, + "args": { + "External id": 1413488,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 5999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2379450, + "ts": 6410534629261.086, "dur": 44.464, + "args": { + "External id": 1413489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 6000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2379450, + "ts": 6410534629262.569, "dur": 42.709, + "args": { + "External id": 1413490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 6001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2379450, + "ts": 6410534629264.164, "dur": 40.809, + "args": { + "External id": 1413491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 6002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629482.459, "dur": 18.867, + "args": { + "External id": 1413492,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 6003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534629524.685, "dur": 15.924, + "args": { + "External id": 1413493,"Record function id": 0, "Ev Idx": 6004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534629528.368, "dur": 10.428, + "args": { + "External id": 1413494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 6005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534629531.994, "dur": 5.631, + "args": { + "External id": 1413495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 6006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534629533.294, "dur": 4.223, + "args": { + "External id": 1413496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 6007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629544.701, "dur": 15.305, + "args": { + "External id": 1413497,"Record function id": 0, "Sequence number": 15109270, "Fwd thread id": 1, "Ev Idx": 6008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629546.153, "dur": 9.947, + "args": { + "External id": 1413498,"Sequence number": 15109270, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6009 + } + }, + { + "ph": "f", "id": 249, "pid": 2338710, "tid": 2379450, "ts": 6410534629546.153, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534629550.374, "dur": 5.445, + "args": { + "External id": 1413499,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534629552.017, "dur": 3.580, + "args": { + "External id": 1413500,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629563.979, "dur": 82.725, + "args": { + "External id": 1413501,"Record function id": 0, "Sequence number": 15109269, "Fwd thread id": 1, "Ev Idx": 6012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629565.139, "dur": 74.837, + "args": { + "External id": 1413502,"Sequence number": 15109269, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6013 + } + }, + { + "ph": "f", "id": 250, "pid": 2338710, "tid": 2379450, "ts": 6410534629565.139, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534629567.223, "dur": 72.282, + "args": { + "External id": 1413503,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 6014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534629573.476, "dur": 26.671, + "args": { + "External id": 1413504,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534629575.714, "dur": 3.673, + "args": { + "External id": 1413505,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629580.516, "dur": 19.281, + "args": { + "External id": 1413506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629582.831, "dur": 16.398, + "args": { + "External id": 1413507,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534629601.878, "dur": 5.047, + "args": { + "External id": 1413508,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 6019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534629605.109, "dur": 1.425, + "args": { + "External id": 1413509,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 6020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629608.748, "dur": 29.750, + "args": { + "External id": 1413510,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629651.459, "dur": 63.710, + "args": { + "External id": 1413511,"Record function id": 0, "Sequence number": 15109268, "Fwd thread id": 1, "Ev Idx": 6022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629652.538, "dur": 58.087, + "args": { + "External id": 1413512,"Sequence number": 15109268, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6023 + } + }, + { + "ph": "f", "id": 251, "pid": 2338710, "tid": 2379450, "ts": 6410534629652.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534629655.432, "dur": 54.867, + "args": { + "External id": 1413513,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 6024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534629657.818, "dur": 22.638, + "args": { + "External id": 1413514,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534629658.906, "dur": 3.284, + "args": { + "External id": 1413515,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629665.214, "dur": 14.954, + "args": { + "External id": 1413516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629668.744, "dur": 10.984, + "args": { + "External id": 1413517,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 6028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410534629681.818, "dur": 10.367, + "args": { + "External id": 1413518,"Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534629687.882, "dur": 3.637, + "args": { + "External id": 1413519,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629693.321, "dur": 16.277, + "args": { + "External id": 1413520,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629719.432, "dur": 137.549, + "args": { + "External id": 1413521,"Record function id": 0, "Sequence number": 15109267, "Fwd thread id": 1, "Ev Idx": 6032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629720.759, "dur": 131.177, + "args": { + "External id": 1413522,"Sequence number": 15109267, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6033 + } + }, + { + "ph": "f", "id": 252, "pid": 2338710, "tid": 2379450, "ts": 6410534629720.759, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534629723.165, "dur": 128.193, + "args": { + "External id": 1413523,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534629724.649, "dur": 28.367, + "args": { + "External id": 1413524,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534629725.807, "dur": 2.440, + "args": { + "External id": 1413525,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629734.037, "dur": 18.698, + "args": { + "External id": 1413526,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629739.067, "dur": 13.266, + "args": { + "External id": 1413527,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 6038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534629754.325, "dur": 3.433, + "args": { + "External id": 1413528,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 6039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534629756.789, "dur": 0.680, + "args": { + "External id": 1413529,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629758.652, "dur": 91.841, + "args": { + "External id": 1413530,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 6041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629863.674, "dur": 115.507, + "args": { + "External id": 1413531,"Record function id": 0, "Sequence number": 15109266, "Fwd thread id": 1, "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534629864.926, "dur": 91.525, + "args": { + "External id": 1413532,"Sequence number": 15109266, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6043 + } + }, + { + "ph": "f", "id": 253, "pid": 2338710, "tid": 2379450, "ts": 6410534629864.926, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534629867.605, "dur": 88.290, + "args": { + "External id": 1413533,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 6044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2379450, + "ts": 6410534629869.207, "dur": 19.157, + "args": { + "External id": 1413534,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534629870.307, "dur": 2.602, + "args": { + "External id": 1413535,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629874.000, "dur": 14.045, + "args": { + "External id": 1413536,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629875.071, "dur": 12.589, + "args": { + "External id": 1413537,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 6048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534629891.993, "dur": 3.457, + "args": { + "External id": 1413538,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 6049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534629894.604, "dur": 0.606, + "args": { + "External id": 1413539,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629896.149, "dur": 58.857, + "args": { + "External id": 1413540,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 6051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534629961.755, "dur": 14.858, + "args": { + "External id": 1413541,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 6052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534629986.899, "dur": 449.060, + "args": { + "External id": 1413542,"Record function id": 0, "Sequence number": 15109265, "Fwd thread id": 1, "Ev Idx": 6053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534629988.796, "dur": 419.913, + "args": { + "External id": 1413543,"Sequence number": 15109265, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6054 + } + }, + { + "ph": "f", "id": 254, "pid": 2338710, "tid": 2379450, "ts": 6410534629988.796, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410534630214.962, "dur": 53.610, + "args": { + "External id": 1413544,"kernel_hash": "c2hiad6vohc5juoazzm5elv5p6zjifqe63zwhygqq3luayunx4no", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "131072", "4096", "1", "993", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/2h/c2hiad6vohc5juoazzm5elv5p6zjifqe63zwhygqq3luayunx4no.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[131072, 4096], [4096], [131072, 4096], [131072, 4096], [132, 4096], [131072], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_0", "pid": 2338710, "tid": 2379450, + "ts": 6410534630307.239, "dur": 30.536, + "args": { + "External id": 1413545,"kernel_hash": "c6346guyxknvaslrs2ei3ec2tw4wgztd2bkmy2hswhmzwewgk7bb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/63/c6346guyxknvaslrs2ei3ec2tw4wgztd2bkmy2hswhmzwewgk7bb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 6056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_1", "pid": 2338710, "tid": 2379450, + "ts": 6410534630357.453, "dur": 24.095, + "args": { + "External id": 1413546,"kernel_hash": "cey5irmf4ovxj63ncyq4qfgp27xz4mzqhlhvmoqbijvnsrskn4ba", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/ey/cey5irmf4ovxj63ncyq4qfgp27xz4mzqhlhvmoqbijvnsrskn4ba.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534630450.003, "dur": 14.705, + "args": { + "External id": 1413547,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534630452.943, "dur": 10.726, + "args": { + "External id": 1413548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534630456.729, "dur": 5.604, + "args": { + "External id": 1413549,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534630458.319, "dur": 3.895, + "args": { + "External id": 1413550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: StackBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534630469.466, "dur": 46.427, + "args": { + "External id": 1413551,"Record function id": 0, "Sequence number": 15109264, "Fwd thread id": 1, "Ev Idx": 6062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534630470.773, "dur": 32.541, + "args": { + "External id": 1413552,"Sequence number": 15109264, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6063 + } + }, + { + "ph": "f", "id": 255, "pid": 2338710, "tid": 2379450, "ts": 6410534630470.773, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410534630473.564, "dur": 10.874, + "args": { + "External id": 1413553,"Record function id": 0, "Concrete Inputs": ["", "-2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630480.487, "dur": 1.557, + "args": { + "External id": 1413554,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410534630485.314, "dur": 7.026, + "args": { + "External id": 1413555,"Record function id": 0, "Concrete Inputs": ["", "-2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630490.048, "dur": 0.633, + "args": { + "External id": 1413556,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410534630492.969, "dur": 4.061, + "args": { + "External id": 1413557,"Record function id": 0, "Concrete Inputs": ["", "-2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630495.409, "dur": 0.534, + "args": { + "External id": 1413558,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2379450, + "ts": 6410534630497.853, "dur": 4.700, + "args": { + "External id": 1413559,"Record function id": 0, "Concrete Inputs": ["", "-2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630500.833, "dur": 0.487, + "args": { + "External id": 1413560,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534630520.507, "dur": 8.036, + "args": { + "External id": 1413561,"Record function id": 0, "Sequence number": 15109263, "Fwd thread id": 1, "Ev Idx": 6072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534630521.839, "dur": 1.347, + "args": { + "External id": 1413562,"Sequence number": 15109263, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6073 + } + }, + { + "ph": "f", "id": 256, "pid": 2338710, "tid": 2379450, "ts": 6410534630521.839, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534630533.951, "dur": 648.568, + "args": { + "External id": 1413563,"Record function id": 0, "Sequence number": 15109262, "Fwd thread id": 1, "Ev Idx": 6074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534630535.295, "dur": 625.553, + "args": { + "External id": 1413564,"Sequence number": 15109262, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6075 + } + }, + { + "ph": "f", "id": 257, "pid": 2338710, "tid": 2379450, "ts": 6410534630535.295, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534630587.769, "dur": 11.721, + "args": { + "External id": 1413565,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534630594.660, "dur": 4.480, + "args": { + "External id": 1413566,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 6077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534630605.666, "dur": 11.262, + "args": { + "External id": 1413567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534630609.612, "dur": 5.901, + "args": { + "External id": 1413568,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630614.517, "dur": 0.741, + "args": { + "External id": 1413569,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2379450, + "ts": 6410534630622.492, "dur": 147.298, + "args": { + "External id": 1413570,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 6081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534630624.113, "dur": 6.347, + "args": { + "External id": 1413571,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 6082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534630624.908, "dur": 4.652, + "args": { + "External id": 1413572,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630626.574, "dur": 2.795, + "args": { + "External id": 1413573,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2379450, + "ts": 6410534630636.340, "dur": 132.524, + "args": { + "External id": 1413574,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534630638.975, "dur": 128.710, + "args": { + "External id": 1413575,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534630779.794, "dur": 5.973, + "args": { + "External id": 1413576,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 6087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534630782.314, "dur": 3.253, + "args": { + "External id": 1413577,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534630830.340, "dur": 8.521, + "args": { + "External id": 1413578,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534630840.661, "dur": 2.081, + "args": { + "External id": 1413579,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534630844.085, "dur": 2.422, + "args": { + "External id": 1413580,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534630893.393, "dur": 3.392, + "args": { + "External id": 1413581,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534630894.705, "dur": 1.874, + "args": { + "External id": 1413582,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338710, "tid": 2379450, + "ts": 6410534630927.317, "dur": 202.219, + "args": { + "External id": 1413583,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 6094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410534630933.965, "dur": 6.793, + "args": { + "External id": 1413584,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630938.814, "dur": 0.888, + "args": { + "External id": 1413585,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534630943.220, "dur": 10.025, + "args": { + "External id": 1413586,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 6097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630949.674, "dur": 2.691, + "args": { + "External id": 1413587,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 6098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410534630955.228, "dur": 3.003, + "args": { + "External id": 1413588,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630957.194, "dur": 0.622, + "args": { + "External id": 1413589,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534630959.331, "dur": 3.330, + "args": { + "External id": 1413590,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630961.533, "dur": 0.595, + "args": { + "External id": 1413591,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 6102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534630969.416, "dur": 3.396, + "args": { + "External id": 1413592,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 6103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630971.701, "dur": 0.677, + "args": { + "External id": 1413593,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 6104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534630973.895, "dur": 7.931, + "args": { + "External id": 1413594,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 6105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534630978.514, "dur": 3.115, + "args": { + "External id": 1413595,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 6106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534630983.283, "dur": 3.007, + "args": { + "External id": 1413596,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 6107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534630985.202, "dur": 0.652, + "args": { + "External id": 1413597,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 6108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534630987.243, "dur": 3.471, + "args": { + "External id": 1413598,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534630988.469, "dur": 2.143, + "args": { + "External id": 1413599,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410534630992.773, "dur": 116.621, + "args": { + "External id": 1413600,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 6111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534631114.195, "dur": 4.554, + "args": { + "External id": 1413601,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 6112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534631120.192, "dur": 4.432, + "args": { + "External id": 1413602,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631122.579, "dur": 0.785, + "args": { + "External id": 1413603,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534631127.276, "dur": 1.124, + "args": { + "External id": 1413604,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 6115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534631198.917, "dur": 12.468, + "args": { + "External id": 1413605,"Record function id": 0, "Ev Idx": 6116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534631201.780, "dur": 8.688, + "args": { + "External id": 1413606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534631205.023, "dur": 4.278, + "args": { + "External id": 1413607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534631206.279, "dur": 2.896, + "args": { + "External id": 1413608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631216.083, "dur": 10.363, + "args": { + "External id": 1413609,"Record function id": 0, "Sequence number": 15109261, "Fwd thread id": 1, "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631217.541, "dur": 4.940, + "args": { + "External id": 1413610,"Sequence number": 15109261, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6121 + } + }, + { + "ph": "f", "id": 258, "pid": 2338710, "tid": 2379450, "ts": 6410534631217.541, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534631220.015, "dur": 2.249, + "args": { + "External id": 1413611,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534631221.039, "dur": 1.065, + "args": { + "External id": 1413612,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631233.234, "dur": 165.676, + "args": { + "External id": 1413613,"Record function id": 0, "Sequence number": 15109260, "Fwd thread id": 1, "Ev Idx": 6124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631234.545, "dur": 155.181, + "args": { + "External id": 1413614,"Sequence number": 15109260, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6125 + } + }, + { + "ph": "f", "id": 259, "pid": 2338710, "tid": 2379450, "ts": 6410534631234.545, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534631240.502, "dur": 5.629, + "args": { + "External id": 1413615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534631242.320, "dur": 2.906, + "args": { + "External id": 1413616,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631244.235, "dur": 0.818, + "args": { + "External id": 1413617,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534631248.066, "dur": 71.043, + "args": { + "External id": 1413618,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534631320.888, "dur": 7.244, + "args": { + "External id": 1413619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534631324.213, "dur": 3.082, + "args": { + "External id": 1413620,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631325.975, "dur": 1.090, + "args": { + "External id": 1413621,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534631330.479, "dur": 4.820, + "args": { + "External id": 1413622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534631332.027, "dur": 2.678, + "args": { + "External id": 1413623,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631334.218, "dur": 0.361, + "args": { + "External id": 1413624,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534631336.128, "dur": 52.380, + "args": { + "External id": 1413625,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631404.597, "dur": 32.700, + "args": { + "External id": 1413626,"Record function id": 0, "Sequence number": 15109259, "Fwd thread id": 1, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631405.982, "dur": 28.257, + "args": { + "External id": 1413627,"Sequence number": 15109259, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6138 + } + }, + { + "ph": "f", "id": 260, "pid": 2338710, "tid": 2379450, "ts": 6410534631405.982, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534631410.546, "dur": 23.489, + "args": { + "External id": 1413628,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534631411.855, "dur": 21.630, + "args": { + "External id": 1413629,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631444.879, "dur": 47.006, + "args": { + "External id": 1413630,"Record function id": 0, "Sequence number": 15109258, "Fwd thread id": 1, "Ev Idx": 6141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631446.213, "dur": 42.144, + "args": { + "External id": 1413631,"Sequence number": 15109258, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6142 + } + }, + { + "ph": "f", "id": 261, "pid": 2338710, "tid": 2379450, "ts": 6410534631446.213, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534631447.489, "dur": 40.606, + "args": { + "External id": 1413632,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534631483.949, "dur": 3.451, + "args": { + "External id": 1418241,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631486.538, "dur": 0.721, + "args": { + "External id": 1418242,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534631497.327, "dur": 10.114, + "args": { + "External id": 1418243,"Record function id": 0, "Ev Idx": 6146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534631498.966, "dur": 7.863, + "args": { + "External id": 1418244,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534631500.741, "dur": 5.681, + "args": { + "External id": 1418245,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534631504.444, "dur": 1.871, + "args": { + "External id": 1418246,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631511.058, "dur": 8.545, + "args": { + "External id": 1418247,"Record function id": 0, "Sequence number": 15109257, "Fwd thread id": 1, "Ev Idx": 6150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631512.229, "dur": 3.415, + "args": { + "External id": 1418248,"Sequence number": 15109257, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6151 + } + }, + { + "ph": "f", "id": 262, "pid": 2338710, "tid": 2379450, "ts": 6410534631512.229, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534631513.594, "dur": 1.901, + "args": { + "External id": 1418249,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534631514.266, "dur": 1.070, + "args": { + "External id": 1418250,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631523.529, "dur": 139.853, + "args": { + "External id": 1418251,"Record function id": 0, "Sequence number": 15109256, "Fwd thread id": 1, "Ev Idx": 6154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631524.547, "dur": 126.858, + "args": { + "External id": 1418252,"Sequence number": 15109256, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6155 + } + }, + { + "ph": "f", "id": 263, "pid": 2338710, "tid": 2379450, "ts": 6410534631524.547, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534631528.467, "dur": 5.573, + "args": { + "External id": 1418253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534631531.565, "dur": 1.924, + "args": { + "External id": 1418254,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631532.875, "dur": 0.503, + "args": { + "External id": 1418255,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534631535.437, "dur": 59.540, + "args": { + "External id": 1418256,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534631596.614, "dur": 4.627, + "args": { + "External id": 1418257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534631597.512, "dur": 3.024, + "args": { + "External id": 1418258,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631599.603, "dur": 0.807, + "args": { + "External id": 1418259,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534631605.299, "dur": 3.617, + "args": { + "External id": 1418260,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534631606.356, "dur": 1.862, + "args": { + "External id": 1418261,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631607.696, "dur": 0.442, + "args": { + "External id": 1418262,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534631609.469, "dur": 40.889, + "args": { + "External id": 1418263,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631671.282, "dur": 40.557, + "args": { + "External id": 1418264,"Record function id": 0, "Sequence number": 15109255, "Fwd thread id": 1, "Ev Idx": 6167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631672.232, "dur": 4.008, + "args": { + "External id": 1418265,"Sequence number": 15109255, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6168 + } + }, + { + "ph": "f", "id": 264, "pid": 2338710, "tid": 2379450, "ts": 6410534631672.232, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534631673.947, "dur": 2.129, + "args": { + "External id": 1418266,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534631674.720, "dur": 1.207, + "args": { + "External id": 1418267,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534631680.525, "dur": 27.658, + "args": { + "External id": 1418268,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631717.209, "dur": 12.481, + "args": { + "External id": 1418269,"Record function id": 0, "Sequence number": 15109254, "Fwd thread id": 1, "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534631720.599, "dur": 5.737, + "args": { + "External id": 1418270,"Sequence number": 15109254, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6173 + } + }, + { + "ph": "f", "id": 265, "pid": 2338710, "tid": 2379450, "ts": 6410534631720.599, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534631721.600, "dur": 4.485, + "args": { + "External id": 1418271,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534631722.456, "dur": 2.806, + "args": { + "External id": 1418272,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534631724.572, "dur": 0.557, + "args": { + "External id": 1418273,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534631734.569, "dur": 5.820, + "args": { + "External id": 1418274,"Record function id": 0, "Ev Idx": 6177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534631736.081, "dur": 3.644, + "args": { + "External id": 1418275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534631737.305, "dur": 1.971, + "args": { + "External id": 1418276,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534631737.890, "dur": 1.279, + "args": { + "External id": 1418277,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534631745.487, "dur": 591.683, + "args": { + "External id": 1418278,"Record function id": 0, "Sequence number": 15109253, "Fwd thread id": 1, "Ev Idx": 6181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534631747.310, "dur": 568.766, + "args": { + "External id": 1418279,"Sequence number": 15109253, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 6182 + } + }, + { + "ph": "f", "id": 266, "pid": 2338710, "tid": 2379450, "ts": 6410534631747.310, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2379450, + "ts": 6410534631778.359, "dur": 40.950, + "args": { + "External id": 1418280,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534631780.398, "dur": 38.678, + "args": { + "External id": 1418281,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534631784.704, "dur": 7.737, + "args": { + "External id": 1418282,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 6185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534631787.882, "dur": 3.632, + "args": { + "External id": 1418283,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534631794.090, "dur": 24.416, + "args": { + "External id": 1418284,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534631838.192, "dur": 2.999, + "args": { + "External id": 1418285,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534631839.179, "dur": 1.824, + "args": { + "External id": 1418286,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534631846.118, "dur": 1.679, + "args": { + "External id": 1418287,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534631846.901, "dur": 0.787, + "args": { + "External id": 1418288,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534631865.547, "dur": 4.968, + "args": { + "External id": 1418289,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534631884.834, "dur": 2.982, + "args": { + "External id": 1418290,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632172.782, "dur": 4.423, + "args": { + "External id": 1418291,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534632183.030, "dur": 46.048, + "args": { + "External id": 1418292,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632199.870, "dur": 1.171, + "args": { + "External id": 1418293,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534632237.518, "dur": 37.097, + "args": { + "External id": 1418294,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534632239.597, "dur": 34.553, + "args": { + "External id": 1418295,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632247.570, "dur": 4.754, + "args": { + "External id": 1418296,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534632254.261, "dur": 19.369, + "args": { + "External id": 1418297,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534632280.606, "dur": 2.764, + "args": { + "External id": 1418298,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632282.052, "dur": 1.147, + "args": { + "External id": 1418299,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534632293.329, "dur": 2.901, + "args": { + "External id": 1418300,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632295.083, "dur": 1.030, + "args": { + "External id": 1418301,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534632299.139, "dur": 5.366, + "args": { + "External id": 1418302,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632302.717, "dur": 1.681, + "args": { + "External id": 1418303,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534632353.783, "dur": 11.228, + "args": { + "External id": 1418304,"Record function id": 0, "Ev Idx": 6207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534632356.748, "dur": 7.362, + "args": { + "External id": 1418305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534632359.485, "dur": 3.413, + "args": { + "External id": 1418306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534632360.689, "dur": 2.090, + "args": { + "External id": 1418307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632368.853, "dur": 12.559, + "args": { + "External id": 1418308,"Record function id": 0, "Sequence number": 15109252, "Fwd thread id": 1, "Ev Idx": 6211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632370.503, "dur": 7.710, + "args": { + "External id": 1418309,"Sequence number": 15109252, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6212 + } + }, + { + "ph": "f", "id": 267, "pid": 2338710, "tid": 2379450, "ts": 6410534632370.503, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534632372.934, "dur": 4.981, + "args": { + "External id": 1418310,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632376.136, "dur": 1.521, + "args": { + "External id": 1418311,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632385.390, "dur": 199.844, + "args": { + "External id": 1418312,"Record function id": 0, "Sequence number": 15109251, "Fwd thread id": 1, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632386.514, "dur": 191.294, + "args": { + "External id": 1418313,"Sequence number": 15109251, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6216 + } + }, + { + "ph": "f", "id": 268, "pid": 2338710, "tid": 2379450, "ts": 6410534632386.514, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534632391.285, "dur": 6.063, + "args": { + "External id": 1418314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534632393.095, "dur": 3.489, + "args": { + "External id": 1418315,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632395.277, "dur": 0.984, + "args": { + "External id": 1418316,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534632398.781, "dur": 106.094, + "args": { + "External id": 1418317,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534632508.100, "dur": 8.721, + "args": { + "External id": 1418318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534632511.874, "dur": 3.725, + "args": { + "External id": 1418319,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632514.224, "dur": 1.212, + "args": { + "External id": 1418320,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534632518.951, "dur": 7.207, + "args": { + "External id": 1418321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534632520.561, "dur": 4.945, + "args": { + "External id": 1418322,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632522.019, "dur": 3.369, + "args": { + "External id": 1418323,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534632527.153, "dur": 49.500, + "args": { + "External id": 1418324,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632593.189, "dur": 10.665, + "args": { + "External id": 1418325,"Record function id": 0, "Sequence number": 15109250, "Fwd thread id": 1, "Ev Idx": 6228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632594.853, "dur": 5.941, + "args": { + "External id": 1418326,"Sequence number": 15109250, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6229 + } + }, + { + "ph": "f", "id": 269, "pid": 2338710, "tid": 2379450, "ts": 6410534632594.853, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534632597.489, "dur": 3.099, + "args": { + "External id": 1418327,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632599.031, "dur": 1.408, + "args": { + "External id": 1418328,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632608.421, "dur": 15.963, + "args": { + "External id": 1418329,"Record function id": 0, "Sequence number": 15109249, "Fwd thread id": 1, "Ev Idx": 6232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632609.387, "dur": 11.498, + "args": { + "External id": 1418330,"Sequence number": 15109249, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6233 + } + }, + { + "ph": "f", "id": 270, "pid": 2338710, "tid": 2379450, "ts": 6410534632609.387, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534632613.572, "dur": 7.013, + "args": { + "External id": 1418331,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534632614.590, "dur": 5.305, + "args": { + "External id": 1418332,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632616.714, "dur": 2.956, + "args": { + "External id": 1418333,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534632629.693, "dur": 7.961, + "args": { + "External id": 1418334,"Record function id": 0, "Ev Idx": 6237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534632631.453, "dur": 5.541, + "args": { + "External id": 1418335,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534632633.375, "dur": 3.239, + "args": { + "External id": 1418336,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534632634.619, "dur": 1.869, + "args": { + "External id": 1418337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632641.459, "dur": 9.659, + "args": { + "External id": 1418338,"Record function id": 0, "Sequence number": 15109248, "Fwd thread id": 1, "Ev Idx": 6241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534632642.491, "dur": 5.480, + "args": { + "External id": 1418339,"Sequence number": 15109248, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6242 + } + }, + { + "ph": "f", "id": 271, "pid": 2338710, "tid": 2379450, "ts": 6410534632642.491, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534632644.878, "dur": 2.912, + "args": { + "External id": 1418340,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632646.232, "dur": 1.386, + "args": { + "External id": 1418341,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534632657.045, "dur": 499.458, + "args": { + "External id": 1418342,"Record function id": 0, "Sequence number": 15109247, "Fwd thread id": 1, "Ev Idx": 6245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534632658.596, "dur": 469.440, + "args": { + "External id": 1418343,"Sequence number": 15109247, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6246 + } + }, + { + "ph": "f", "id": 272, "pid": 2338710, "tid": 2379450, "ts": 6410534632658.596, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534632681.971, "dur": 11.078, + "args": { + "External id": 1418344,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632686.107, "dur": 6.283, + "args": { + "External id": 1418345,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534632695.765, "dur": 4.717, + "args": { + "External id": 1418346,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632697.490, "dur": 2.749, + "args": { + "External id": 1418347,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534632702.571, "dur": 6.155, + "args": { + "External id": 1418348,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632704.851, "dur": 3.643, + "args": { + "External id": 1418349,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534632750.459, "dur": 301.004, + "args": { + "External id": 1418350,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 6253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534632864.514, "dur": 3.756, + "args": { + "External id": 1418351,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534632870.545, "dur": 3.802, + "args": { + "External id": 1418352,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534632875.925, "dur": 3.875, + "args": { + "External id": 1418353,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534632881.078, "dur": 2.872, + "args": { + "External id": 1418354,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534632938.486, "dur": 3.331, + "args": { + "External id": 1418355,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632939.935, "dur": 1.706, + "args": { + "External id": 1418356,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534632946.073, "dur": 33.377, + "args": { + "External id": 1418357,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632955.868, "dur": 0.895, + "args": { + "External id": 1418358,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534632981.271, "dur": 1.693, + "args": { + "External id": 1418359,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534632982.390, "dur": 0.498, + "args": { + "External id": 1418360,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534632983.967, "dur": 15.498, + "args": { + "External id": 1418361,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534632986.059, "dur": 0.389, + "args": { + "External id": 1418362,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534633111.718, "dur": 5.092, + "args": { + "External id": 1418363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534633120.692, "dur": 0.687, + "args": { + "External id": 1418364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534633123.334, "dur": 0.797, + "args": { + "External id": 1418365,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534633169.919, "dur": 318.627, + "args": { + "External id": 1418366,"Record function id": 0, "Sequence number": 15109246, "Fwd thread id": 1, "Ev Idx": 6269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534633171.965, "dur": 304.251, + "args": { + "External id": 1418367,"Sequence number": 15109246, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6270 + } + }, + { + "ph": "f", "id": 273, "pid": 2338710, "tid": 2379450, "ts": 6410534633171.965, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534633201.760, "dur": 61.838, + "args": { + "External id": 1418368,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534633206.113, "dur": 5.027, + "args": { + "External id": 1418369,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534633213.205, "dur": 49.731, + "args": { + "External id": 1418370,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 6273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534633277.081, "dur": 5.989, + "args": { + "External id": 1418371,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534633279.981, "dur": 2.765, + "args": { + "External id": 1418372,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534633500.353, "dur": 220.385, + "args": { + "External id": 1418373,"Record function id": 0, "Sequence number": 15109245, "Fwd thread id": 1, "Ev Idx": 6276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534633502.754, "dur": 208.562, + "args": { + "External id": 1418374,"Sequence number": 15109245, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6277 + } + }, + { + "ph": "f", "id": 274, "pid": 2338710, "tid": 2379450, "ts": 6410534633502.754, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534633519.902, "dur": 58.844, + "args": { + "External id": 1418375,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534633523.208, "dur": 4.756, + "args": { + "External id": 1418376,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534633529.490, "dur": 48.375, + "args": { + "External id": 1418377,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 6280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534633588.599, "dur": 5.896, + "args": { + "External id": 1418378,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534633590.779, "dur": 3.378, + "args": { + "External id": 1418379,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633728.615, "dur": 16.664, + "args": { + "External id": 1418380,"Record function id": 0, "Sequence number": 15109244, "Fwd thread id": 1, "Ev Idx": 6283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633730.245, "dur": 10.419, + "args": { + "External id": 1418381,"Sequence number": 15109244, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6284 + } + }, + { + "ph": "f", "id": 275, "pid": 2338710, "tid": 2379450, "ts": 6410534633730.245, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534633733.226, "dur": 7.104, + "args": { + "External id": 1418382,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534633735.185, "dur": 4.914, + "args": { + "External id": 1418383,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633749.446, "dur": 7.834, + "args": { + "External id": 1418384,"Record function id": 0, "Sequence number": 15109243, "Fwd thread id": 1, "Ev Idx": 6287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633750.425, "dur": 4.861, + "args": { + "External id": 1418385,"Sequence number": 15109243, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6288 + } + }, + { + "ph": "f", "id": 276, "pid": 2338710, "tid": 2379450, "ts": 6410534633750.425, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534633752.648, "dur": 2.461, + "args": { + "External id": 1418386,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534633754.009, "dur": 0.948, + "args": { + "External id": 1418387,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633760.823, "dur": 13.255, + "args": { + "External id": 1418388,"Record function id": 0, "Sequence number": 15109242, "Fwd thread id": 1, "Ev Idx": 6291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633765.606, "dur": 6.378, + "args": { + "External id": 1418389,"Sequence number": 15109242, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6292 + } + }, + { + "ph": "f", "id": 277, "pid": 2338710, "tid": 2379450, "ts": 6410534633765.606, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534633769.583, "dur": 2.244, + "args": { + "External id": 1418390,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534633770.675, "dur": 1.006, + "args": { + "External id": 1418391,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633778.058, "dur": 10.631, + "args": { + "External id": 1418392,"Record function id": 0, "Sequence number": 15109241, "Fwd thread id": 1, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633779.064, "dur": 6.554, + "args": { + "External id": 1418393,"Sequence number": 15109241, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6296 + } + }, + { + "ph": "f", "id": 278, "pid": 2338710, "tid": 2379450, "ts": 6410534633779.064, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534633780.922, "dur": 4.533, + "args": { + "External id": 1418394,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534633781.806, "dur": 3.538, + "args": { + "External id": 1418395,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633792.686, "dur": 180.594, + "args": { + "External id": 1418396,"Record function id": 0, "Sequence number": 15109240, "Fwd thread id": 1, "Ev Idx": 6299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633793.930, "dur": 169.166, + "args": { + "External id": 1418397,"Sequence number": 15109240, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6300 + } + }, + { + "ph": "f", "id": 279, "pid": 2338710, "tid": 2379450, "ts": 6410534633793.930, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534633799.651, "dur": 9.924, + "args": { + "External id": 1418398,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534633804.586, "dur": 4.174, + "args": { + "External id": 1418399,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534633806.927, "dur": 1.443, + "args": { + "External id": 1418400,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534633811.295, "dur": 81.084, + "args": { + "External id": 1418401,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534633894.270, "dur": 7.771, + "args": { + "External id": 1418402,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534633895.388, "dur": 5.742, + "args": { + "External id": 1418403,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534633897.538, "dur": 3.335, + "args": { + "External id": 1418404,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534633906.448, "dur": 4.389, + "args": { + "External id": 1418405,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534633907.905, "dur": 2.382, + "args": { + "External id": 1418406,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534633909.613, "dur": 0.577, + "args": { + "External id": 1418407,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534633911.533, "dur": 50.186, + "args": { + "External id": 1418408,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633979.213, "dur": 8.925, + "args": { + "External id": 1418409,"Record function id": 0, "Sequence number": 15109239, "Fwd thread id": 1, "Ev Idx": 6312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633980.422, "dur": 4.998, + "args": { + "External id": 1418410,"Sequence number": 15109239, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6313 + } + }, + { + "ph": "f", "id": 280, "pid": 2338710, "tid": 2379450, "ts": 6410534633980.422, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534633982.804, "dur": 2.416, + "args": { + "External id": 1418411,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534633983.653, "dur": 1.441, + "args": { + "External id": 1418412,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633992.614, "dur": 12.154, + "args": { + "External id": 1418413,"Record function id": 0, "Sequence number": 15109238, "Fwd thread id": 1, "Ev Idx": 6316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534633993.596, "dur": 7.915, + "args": { + "External id": 1418414,"Sequence number": 15109238, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6317 + } + }, + { + "ph": "f", "id": 281, "pid": 2338710, "tid": 2379450, "ts": 6410534633993.596, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534633997.446, "dur": 3.783, + "args": { + "External id": 1418415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534633998.313, "dur": 2.328, + "args": { + "External id": 1418416,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534633999.840, "dur": 0.650, + "args": { + "External id": 1418417,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534634011.704, "dur": 17.936, + "args": { + "External id": 1418418,"Record function id": 0, "Ev Idx": 6321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534634013.836, "dur": 14.824, + "args": { + "External id": 1418419,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534634017.186, "dur": 5.628, + "args": { + "External id": 1418420,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534634018.623, "dur": 4.084, + "args": { + "External id": 1418421,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634033.354, "dur": 8.286, + "args": { + "External id": 1418422,"Record function id": 0, "Sequence number": 15109237, "Fwd thread id": 1, "Ev Idx": 6325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634034.314, "dur": 3.747, + "args": { + "External id": 1418423,"Sequence number": 15109237, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6326 + } + }, + { + "ph": "f", "id": 282, "pid": 2338710, "tid": 2379450, "ts": 6410534634034.314, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534634035.929, "dur": 1.971, + "args": { + "External id": 1418424,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534634036.946, "dur": 0.848, + "args": { + "External id": 1418425,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634047.807, "dur": 183.290, + "args": { + "External id": 1418426,"Record function id": 0, "Sequence number": 15109236, "Fwd thread id": 1, "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634051.734, "dur": 168.893, + "args": { + "External id": 1418427,"Sequence number": 15109236, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6330 + } + }, + { + "ph": "f", "id": 283, "pid": 2338710, "tid": 2379450, "ts": 6410534634051.734, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534634110.508, "dur": 5.058, + "args": { + "External id": 1418428,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534634111.705, "dur": 3.030, + "args": { + "External id": 1418429,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634113.571, "dur": 0.812, + "args": { + "External id": 1418430,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534634116.656, "dur": 41.695, + "args": { + "External id": 1418431,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534634159.814, "dur": 10.960, + "args": { + "External id": 1418432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534634160.624, "dur": 9.413, + "args": { + "External id": 1418433,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634167.079, "dur": 2.795, + "args": { + "External id": 1418434,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534634172.512, "dur": 4.291, + "args": { + "External id": 1418435,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534634174.199, "dur": 2.117, + "args": { + "External id": 1418436,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634175.828, "dur": 0.404, + "args": { + "External id": 1418437,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534634177.502, "dur": 42.248, + "args": { + "External id": 1418438,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634239.179, "dur": 42.480, + "args": { + "External id": 1418439,"Record function id": 0, "Sequence number": 15109235, "Fwd thread id": 1, "Ev Idx": 6342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634240.669, "dur": 5.981, + "args": { + "External id": 1418440,"Sequence number": 15109235, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6343 + } + }, + { + "ph": "f", "id": 284, "pid": 2338710, "tid": 2379450, "ts": 6410534634240.669, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534634243.127, "dur": 3.361, + "args": { + "External id": 1418441,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534634244.335, "dur": 2.039, + "args": { + "External id": 1418442,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534634250.493, "dur": 28.013, + "args": { + "External id": 1418443,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634289.198, "dur": 9.596, + "args": { + "External id": 1418444,"Record function id": 0, "Sequence number": 15109234, "Fwd thread id": 1, "Ev Idx": 6347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634290.533, "dur": 6.195, + "args": { + "External id": 1418445,"Sequence number": 15109234, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6348 + } + }, + { + "ph": "f", "id": 285, "pid": 2338710, "tid": 2379450, "ts": 6410534634290.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534634291.554, "dur": 4.912, + "args": { + "External id": 1418446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534634292.848, "dur": 3.014, + "args": { + "External id": 1418447,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634294.917, "dur": 0.800, + "args": { + "External id": 1418448,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534634303.781, "dur": 7.927, + "args": { + "External id": 1418449,"Record function id": 0, "Ev Idx": 6352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534634305.994, "dur": 5.005, + "args": { + "External id": 1418450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534634307.478, "dur": 2.967, + "args": { + "External id": 1418451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534634308.401, "dur": 1.936, + "args": { + "External id": 1418452,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634315.609, "dur": 10.736, + "args": { + "External id": 1418453,"Record function id": 0, "Sequence number": 15109233, "Fwd thread id": 1, "Ev Idx": 6356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634317.234, "dur": 5.693, + "args": { + "External id": 1418454,"Sequence number": 15109233, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6357 + } + }, + { + "ph": "f", "id": 286, "pid": 2338710, "tid": 2379450, "ts": 6410534634317.234, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534634318.785, "dur": 3.957, + "args": { + "External id": 1418455,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534634321.519, "dur": 1.096, + "args": { + "External id": 1418456,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634330.271, "dur": 135.057, + "args": { + "External id": 1418457,"Record function id": 0, "Sequence number": 15109232, "Fwd thread id": 1, "Ev Idx": 6360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634331.228, "dur": 121.858, + "args": { + "External id": 1418458,"Sequence number": 15109232, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6361 + } + }, + { + "ph": "f", "id": 287, "pid": 2338710, "tid": 2379450, "ts": 6410534634331.228, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534634333.974, "dur": 3.146, + "args": { + "External id": 1418459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534634334.816, "dur": 1.806, + "args": { + "External id": 1418460,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634335.960, "dur": 0.519, + "args": { + "External id": 1418461,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534634340.202, "dur": 39.367, + "args": { + "External id": 1418462,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534634380.980, "dur": 4.290, + "args": { + "External id": 1418463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534634381.608, "dur": 2.910, + "args": { + "External id": 1418464,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634383.089, "dur": 1.272, + "args": { + "External id": 1418465,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534634386.725, "dur": 6.585, + "args": { + "External id": 1418466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534634388.183, "dur": 4.471, + "args": { + "External id": 1418467,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634391.966, "dur": 0.577, + "args": { + "External id": 1418468,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534634394.012, "dur": 57.642, + "args": { + "External id": 1418469,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634473.566, "dur": 32.820, + "args": { + "External id": 1418470,"Record function id": 0, "Sequence number": 15109231, "Fwd thread id": 1, "Ev Idx": 6373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634474.832, "dur": 6.388, + "args": { + "External id": 1418471,"Sequence number": 15109231, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6374 + } + }, + { + "ph": "f", "id": 288, "pid": 2338710, "tid": 2379450, "ts": 6410534634474.832, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534634477.219, "dur": 3.821, + "args": { + "External id": 1418472,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534634478.729, "dur": 2.162, + "args": { + "External id": 1418473,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534634484.282, "dur": 19.413, + "args": { + "External id": 1418474,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634511.181, "dur": 12.589, + "args": { + "External id": 1418475,"Record function id": 0, "Sequence number": 15109230, "Fwd thread id": 1, "Ev Idx": 6378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634512.276, "dur": 8.636, + "args": { + "External id": 1418476,"Sequence number": 15109230, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6379 + } + }, + { + "ph": "f", "id": 289, "pid": 2338710, "tid": 2379450, "ts": 6410534634512.276, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534634513.511, "dur": 7.168, + "args": { + "External id": 1418477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534634514.479, "dur": 5.571, + "args": { + "External id": 1418478,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634519.060, "dur": 0.850, + "args": { + "External id": 1418479,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534634528.816, "dur": 7.285, + "args": { + "External id": 1418480,"Record function id": 0, "Ev Idx": 6383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534634530.391, "dur": 5.070, + "args": { + "External id": 1418481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534634532.001, "dur": 2.823, + "args": { + "External id": 1418482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534634532.881, "dur": 1.834, + "args": { + "External id": 1418483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534634541.030, "dur": 431.412, + "args": { + "External id": 1418484,"Record function id": 0, "Sequence number": 15109229, "Fwd thread id": 1, "Ev Idx": 6387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534634542.869, "dur": 388.067, + "args": { + "External id": 1418485,"Sequence number": 15109229, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6388 + } + }, + { + "ph": "f", "id": 290, "pid": 2338710, "tid": 2379450, "ts": 6410534634542.869, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534634584.528, "dur": 2.515, + "args": { + "External id": 1418486,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534634585.580, "dur": 1.324, + "args": { + "External id": 1418487,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534634605.463, "dur": 5.354, + "args": { + "External id": 1418488,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534634621.851, "dur": 2.241, + "args": { + "External id": 1418489,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534634810.396, "dur": 2.877, + "args": { + "External id": 1418490,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534634818.243, "dur": 42.302, + "args": { + "External id": 1418491,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634832.879, "dur": 1.036, + "args": { + "External id": 1418492,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534634867.463, "dur": 34.135, + "args": { + "External id": 1418493,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534634869.522, "dur": 31.755, + "args": { + "External id": 1418494,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534634875.113, "dur": 5.200, + "args": { + "External id": 1418495,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534634882.235, "dur": 18.434, + "args": { + "External id": 1418496,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534634909.610, "dur": 2.799, + "args": { + "External id": 1418497,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534634910.875, "dur": 1.405, + "args": { + "External id": 1418498,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534634920.083, "dur": 2.759, + "args": { + "External id": 1418499,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534634921.425, "dur": 1.266, + "args": { + "External id": 1418500,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534634945.034, "dur": 19.536, + "args": { + "External id": 1418501,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534634984.570, "dur": 10.283, + "args": { + "External id": 1418502,"Record function id": 0, "Ev Idx": 6405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534634987.203, "dur": 6.851, + "args": { + "External id": 1418503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534634989.547, "dur": 3.332, + "args": { + "External id": 1418504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534634990.533, "dur": 2.178, + "args": { + "External id": 1418505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534634999.952, "dur": 8.458, + "args": { + "External id": 1418506,"Record function id": 0, "Sequence number": 15109228, "Fwd thread id": 1, "Ev Idx": 6409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635002.203, "dur": 1.465, + "args": { + "External id": 1418507,"Sequence number": 15109228, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6410 + } + }, + { + "ph": "f", "id": 291, "pid": 2338710, "tid": 2379450, "ts": 6410534635002.203, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534635012.894, "dur": 573.441, + "args": { + "External id": 1418508,"Record function id": 0, "Sequence number": 15109227, "Fwd thread id": 1, "Ev Idx": 6411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534635014.554, "dur": 556.558, + "args": { + "External id": 1418509,"Sequence number": 15109227, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6412 + } + }, + { + "ph": "f", "id": 292, "pid": 2338710, "tid": 2379450, "ts": 6410534635014.554, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534635052.539, "dur": 55.278, + "args": { + "External id": 1418510,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534635101.911, "dur": 5.333, + "args": { + "External id": 1418511,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 6414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635112.592, "dur": 6.680, + "args": { + "External id": 1418512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635114.555, "dur": 3.834, + "args": { + "External id": 1418513,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635117.110, "dur": 1.084, + "args": { + "External id": 1418514,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2379450, + "ts": 6410534635123.502, "dur": 113.790, + "args": { + "External id": 1418515,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 6418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635126.899, "dur": 6.141, + "args": { + "External id": 1418516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 6419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635127.682, "dur": 4.745, + "args": { + "External id": 1418517,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635129.349, "dur": 2.867, + "args": { + "External id": 1418518,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2379450, + "ts": 6410534635134.481, "dur": 102.095, + "args": { + "External id": 1418519,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534635136.317, "dur": 99.272, + "args": { + "External id": 1418520,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534635242.181, "dur": 3.858, + "args": { + "External id": 1418521,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 6424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635243.905, "dur": 1.972, + "args": { + "External id": 1418522,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534635288.755, "dur": 7.472, + "args": { + "External id": 1418523,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534635297.707, "dur": 2.804, + "args": { + "External id": 1418524,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534635301.703, "dur": 3.153, + "args": { + "External id": 1418525,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534635342.054, "dur": 2.939, + "args": { + "External id": 1418526,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635343.187, "dur": 1.576, + "args": { + "External id": 1418527,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338710, "tid": 2379450, + "ts": 6410534635372.023, "dur": 173.467, + "args": { + "External id": 1418528,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 6431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410534635379.345, "dur": 6.658, + "args": { + "External id": 1418529,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635383.623, "dur": 1.274, + "args": { + "External id": 1418530,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534635387.967, "dur": 5.519, + "args": { + "External id": 1418531,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 6434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635391.889, "dur": 0.734, + "args": { + "External id": 1418532,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 6435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410534635395.016, "dur": 3.189, + "args": { + "External id": 1418533,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635397.123, "dur": 0.732, + "args": { + "External id": 1418534,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534635399.290, "dur": 3.510, + "args": { + "External id": 1418535,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635401.790, "dur": 0.598, + "args": { + "External id": 1418536,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 6439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534635407.057, "dur": 27.025, + "args": { + "External id": 1418537,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 6440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635411.494, "dur": 21.322, + "args": { + "External id": 1418538,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 6441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534635436.516, "dur": 7.930, + "args": { + "External id": 1418539,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 6442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534635441.690, "dur": 2.515, + "args": { + "External id": 1418540,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 6443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534635448.564, "dur": 3.531, + "args": { + "External id": 1418541,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 6444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635451.116, "dur": 0.624, + "args": { + "External id": 1418542,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 6445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534635453.031, "dur": 3.619, + "args": { + "External id": 1418543,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635454.227, "dur": 2.298, + "args": { + "External id": 1418544,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410534635458.194, "dur": 73.556, + "args": { + "External id": 1418545,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 6448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635534.073, "dur": 1.439, + "args": { + "External id": 1418546,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 6449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534635536.610, "dur": 4.173, + "args": { + "External id": 1418547,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 6450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635539.333, "dur": 0.762, + "args": { + "External id": 1418548,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 6451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635543.310, "dur": 0.987, + "args": { + "External id": 1418549,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 6452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534635601.631, "dur": 12.012, + "args": { + "External id": 1418550,"Record function id": 0, "Ev Idx": 6453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534635604.184, "dur": 8.573, + "args": { + "External id": 1418551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534635606.881, "dur": 4.522, + "args": { + "External id": 1418552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534635608.398, "dur": 2.848, + "args": { + "External id": 1418553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635618.250, "dur": 10.810, + "args": { + "External id": 1418554,"Record function id": 0, "Sequence number": 15109226, "Fwd thread id": 1, "Ev Idx": 6457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635619.955, "dur": 5.039, + "args": { + "External id": 1418555,"Sequence number": 15109226, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6458 + } + }, + { + "ph": "f", "id": 293, "pid": 2338710, "tid": 2379450, "ts": 6410534635619.955, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534635622.225, "dur": 2.532, + "args": { + "External id": 1418556,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635623.517, "dur": 1.116, + "args": { + "External id": 1418557,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635633.210, "dur": 137.544, + "args": { + "External id": 1418558,"Record function id": 0, "Sequence number": 15109225, "Fwd thread id": 1, "Ev Idx": 6461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635634.641, "dur": 127.673, + "args": { + "External id": 1418559,"Sequence number": 15109225, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6462 + } + }, + { + "ph": "f", "id": 294, "pid": 2338710, "tid": 2379450, "ts": 6410534635634.641, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635640.153, "dur": 7.446, + "args": { + "External id": 1418560,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635641.558, "dur": 5.404, + "args": { + "External id": 1418561,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635645.937, "dur": 0.860, + "args": { + "External id": 1418562,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534635649.004, "dur": 51.056, + "args": { + "External id": 1418563,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635701.704, "dur": 4.684, + "args": { + "External id": 1418564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635702.699, "dur": 2.960, + "args": { + "External id": 1418565,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635704.530, "dur": 0.921, + "args": { + "External id": 1418566,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635708.480, "dur": 8.737, + "args": { + "External id": 1418567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635711.984, "dur": 4.680, + "args": { + "External id": 1418568,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635713.490, "dur": 3.080, + "args": { + "External id": 1418569,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534635717.823, "dur": 43.314, + "args": { + "External id": 1418570,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635776.555, "dur": 7.888, + "args": { + "External id": 1418571,"Record function id": 0, "Sequence number": 15109224, "Fwd thread id": 1, "Ev Idx": 6474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635777.890, "dur": 5.115, + "args": { + "External id": 1418572,"Sequence number": 15109224, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6475 + } + }, + { + "ph": "f", "id": 295, "pid": 2338710, "tid": 2379450, "ts": 6410534635777.890, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534635780.579, "dur": 2.251, + "args": { + "External id": 1418573,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635781.583, "dur": 1.130, + "args": { + "External id": 1418574,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635788.675, "dur": 11.532, + "args": { + "External id": 1418575,"Record function id": 0, "Sequence number": 15109223, "Fwd thread id": 1, "Ev Idx": 6478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635789.681, "dur": 7.616, + "args": { + "External id": 1418576,"Sequence number": 15109223, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6479 + } + }, + { + "ph": "f", "id": 296, "pid": 2338710, "tid": 2379450, "ts": 6410534635789.681, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635790.572, "dur": 6.453, + "args": { + "External id": 1418577,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635793.477, "dur": 3.002, + "args": { + "External id": 1418578,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635795.735, "dur": 0.616, + "args": { + "External id": 1418579,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534635804.987, "dur": 6.858, + "args": { + "External id": 1418580,"Record function id": 0, "Ev Idx": 6483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534635806.947, "dur": 4.190, + "args": { + "External id": 1418581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534635808.230, "dur": 2.483, + "args": { + "External id": 1418582,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534635809.094, "dur": 1.500, + "args": { + "External id": 1418583,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635816.240, "dur": 7.874, + "args": { + "External id": 1418584,"Record function id": 0, "Sequence number": 15109222, "Fwd thread id": 1, "Ev Idx": 6487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635817.539, "dur": 3.909, + "args": { + "External id": 1418585,"Sequence number": 15109222, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6488 + } + }, + { + "ph": "f", "id": 297, "pid": 2338710, "tid": 2379450, "ts": 6410534635817.539, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534635818.917, "dur": 2.329, + "args": { + "External id": 1418586,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635820.140, "dur": 0.998, + "args": { + "External id": 1418587,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635828.206, "dur": 112.488, + "args": { + "External id": 1418588,"Record function id": 0, "Sequence number": 15109221, "Fwd thread id": 1, "Ev Idx": 6491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635832.280, "dur": 99.130, + "args": { + "External id": 1418589,"Sequence number": 15109221, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6492 + } + }, + { + "ph": "f", "id": 298, "pid": 2338710, "tid": 2379450, "ts": 6410534635832.280, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635834.897, "dur": 2.970, + "args": { + "External id": 1418590,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635835.404, "dur": 1.959, + "args": { + "External id": 1418591,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635836.657, "dur": 0.587, + "args": { + "External id": 1418592,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534635838.686, "dur": 37.586, + "args": { + "External id": 1418593,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635877.743, "dur": 9.064, + "args": { + "External id": 1418594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635878.495, "dur": 7.607, + "args": { + "External id": 1418595,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635882.664, "dur": 3.307, + "args": { + "External id": 1418596,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635888.670, "dur": 4.181, + "args": { + "External id": 1418597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635890.079, "dur": 2.165, + "args": { + "External id": 1418598,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635891.464, "dur": 0.696, + "args": { + "External id": 1418599,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534635893.538, "dur": 36.916, + "args": { + "External id": 1418600,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635946.391, "dur": 37.018, + "args": { + "External id": 1418601,"Record function id": 0, "Sequence number": 15109220, "Fwd thread id": 1, "Ev Idx": 6504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635947.731, "dur": 5.222, + "args": { + "External id": 1418602,"Sequence number": 15109220, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6505 + } + }, + { + "ph": "f", "id": 299, "pid": 2338710, "tid": 2379450, "ts": 6410534635947.731, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534635950.029, "dur": 2.774, + "args": { + "External id": 1418603,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534635951.514, "dur": 1.163, + "args": { + "External id": 1418604,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534635956.116, "dur": 24.073, + "args": { + "External id": 1418605,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635987.607, "dur": 11.956, + "args": { + "External id": 1418606,"Record function id": 0, "Sequence number": 15109219, "Fwd thread id": 1, "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534635988.829, "dur": 8.366, + "args": { + "External id": 1418607,"Sequence number": 15109219, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6510 + } + }, + { + "ph": "f", "id": 300, "pid": 2338710, "tid": 2379450, "ts": 6410534635988.829, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534635992.383, "dur": 4.552, + "args": { + "External id": 1418608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534635993.480, "dur": 2.825, + "args": { + "External id": 1418609,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534635995.551, "dur": 0.615, + "args": { + "External id": 1418610,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534636004.455, "dur": 6.134, + "args": { + "External id": 1418611,"Record function id": 0, "Ev Idx": 6514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534636006.382, "dur": 3.611, + "args": { + "External id": 1418612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534636007.694, "dur": 1.917, + "args": { + "External id": 1418613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534636008.250, "dur": 1.276, + "args": { + "External id": 1418614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534636015.379, "dur": 591.605, + "args": { + "External id": 1418615,"Record function id": 0, "Sequence number": 15109218, "Fwd thread id": 1, "Ev Idx": 6518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534636017.010, "dur": 541.119, + "args": { + "External id": 1418616,"Sequence number": 15109218, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 6519 + } + }, + { + "ph": "f", "id": 301, "pid": 2338710, "tid": 2379450, "ts": 6410534636017.010, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2379450, + "ts": 6410534636043.006, "dur": 102.139, + "args": { + "External id": 1418617,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534636044.967, "dur": 99.780, + "args": { + "External id": 1418618,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534636048.347, "dur": 64.257, + "args": { + "External id": 1418619,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 6522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534636051.498, "dur": 59.840, + "args": { + "External id": 1418620,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534636115.112, "dur": 28.830, + "args": { + "External id": 1418621,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534636162.304, "dur": 7.934, + "args": { + "External id": 1418622,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636165.836, "dur": 4.284, + "args": { + "External id": 1418623,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534636174.958, "dur": 2.590, + "args": { + "External id": 1418624,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636176.042, "dur": 1.398, + "args": { + "External id": 1418625,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534636193.688, "dur": 3.627, + "args": { + "External id": 1418626,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534636212.154, "dur": 2.786, + "args": { + "External id": 1418627,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636404.507, "dur": 3.505, + "args": { + "External id": 1418628,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534636412.974, "dur": 63.476, + "args": { + "External id": 1418629,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636444.749, "dur": 1.251, + "args": { + "External id": 1418630,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534636483.900, "dur": 33.666, + "args": { + "External id": 1418631,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534636486.039, "dur": 31.282, + "args": { + "External id": 1418632,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636491.311, "dur": 5.514, + "args": { + "External id": 1418633,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534636498.400, "dur": 18.440, + "args": { + "External id": 1418634,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534636524.975, "dur": 3.488, + "args": { + "External id": 1418635,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636526.605, "dur": 1.686, + "args": { + "External id": 1418636,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534636537.231, "dur": 2.474, + "args": { + "External id": 1418637,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636538.321, "dur": 1.263, + "args": { + "External id": 1418638,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534636542.240, "dur": 4.465, + "args": { + "External id": 1418639,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636543.445, "dur": 3.154, + "args": { + "External id": 1418640,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534636584.110, "dur": 20.933, + "args": { + "External id": 1418641,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534636623.819, "dur": 11.336, + "args": { + "External id": 1418642,"Record function id": 0, "Ev Idx": 6545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534636626.500, "dur": 7.666, + "args": { + "External id": 1418643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534636629.421, "dur": 3.684, + "args": { + "External id": 1418644,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534636630.804, "dur": 2.147, + "args": { + "External id": 1418645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636639.918, "dur": 10.566, + "args": { + "External id": 1418646,"Record function id": 0, "Sequence number": 15109217, "Fwd thread id": 1, "Ev Idx": 6549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636641.668, "dur": 5.052, + "args": { + "External id": 1418647,"Sequence number": 15109217, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6550 + } + }, + { + "ph": "f", "id": 302, "pid": 2338710, "tid": 2379450, "ts": 6410534636641.668, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534636643.801, "dur": 2.654, + "args": { + "External id": 1418648,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636644.931, "dur": 1.383, + "args": { + "External id": 1418649,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636654.680, "dur": 169.726, + "args": { + "External id": 1418650,"Record function id": 0, "Sequence number": 15109216, "Fwd thread id": 1, "Ev Idx": 6553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636656.180, "dur": 159.254, + "args": { + "External id": 1418651,"Sequence number": 15109216, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6554 + } + }, + { + "ph": "f", "id": 303, "pid": 2338710, "tid": 2379450, "ts": 6410534636656.180, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534636663.472, "dur": 5.920, + "args": { + "External id": 1418652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534636664.945, "dur": 3.670, + "args": { + "External id": 1418653,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636667.280, "dur": 1.033, + "args": { + "External id": 1418654,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534636670.720, "dur": 84.222, + "args": { + "External id": 1418655,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534636756.385, "dur": 6.303, + "args": { + "External id": 1418656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534636757.481, "dur": 4.439, + "args": { + "External id": 1418657,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636759.339, "dur": 2.345, + "args": { + "External id": 1418658,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534636766.571, "dur": 4.602, + "args": { + "External id": 1418659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534636768.273, "dur": 2.341, + "args": { + "External id": 1418660,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636770.139, "dur": 0.316, + "args": { + "External id": 1418661,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534636771.700, "dur": 42.601, + "args": { + "External id": 1418662,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636830.351, "dur": 9.726, + "args": { + "External id": 1418663,"Record function id": 0, "Sequence number": 15109215, "Fwd thread id": 1, "Ev Idx": 6566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636831.560, "dur": 5.307, + "args": { + "External id": 1418664,"Sequence number": 15109215, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6567 + } + }, + { + "ph": "f", "id": 304, "pid": 2338710, "tid": 2379450, "ts": 6410534636831.560, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534636833.708, "dur": 2.951, + "args": { + "External id": 1418665,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636835.221, "dur": 1.320, + "args": { + "External id": 1418666,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636843.972, "dur": 10.941, + "args": { + "External id": 1418667,"Record function id": 0, "Sequence number": 15109214, "Fwd thread id": 1, "Ev Idx": 6570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636845.235, "dur": 7.165, + "args": { + "External id": 1418668,"Sequence number": 15109214, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6571 + } + }, + { + "ph": "f", "id": 305, "pid": 2338710, "tid": 2379450, "ts": 6410534636845.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534636846.172, "dur": 5.976, + "args": { + "External id": 1418669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534636847.157, "dur": 4.412, + "args": { + "External id": 1418670,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636850.949, "dur": 0.469, + "args": { + "External id": 1418671,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534636859.664, "dur": 9.291, + "args": { + "External id": 1418672,"Record function id": 0, "Ev Idx": 6575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534636861.740, "dur": 6.614, + "args": { + "External id": 1418673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534636863.110, "dur": 4.920, + "args": { + "External id": 1418674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534636863.678, "dur": 4.208, + "args": { + "External id": 1418675,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636873.220, "dur": 8.000, + "args": { + "External id": 1418676,"Record function id": 0, "Sequence number": 15109213, "Fwd thread id": 1, "Ev Idx": 6579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534636874.332, "dur": 4.214, + "args": { + "External id": 1418677,"Sequence number": 15109213, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6580 + } + }, + { + "ph": "f", "id": 306, "pid": 2338710, "tid": 2379450, "ts": 6410534636874.332, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534636875.830, "dur": 2.509, + "args": { + "External id": 1418678,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534636876.859, "dur": 1.348, + "args": { + "External id": 1418679,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534636886.326, "dur": 466.947, + "args": { + "External id": 1418680,"Record function id": 0, "Sequence number": 15109212, "Fwd thread id": 1, "Ev Idx": 6583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534636887.851, "dur": 434.511, + "args": { + "External id": 1418681,"Sequence number": 15109212, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6584 + } + }, + { + "ph": "f", "id": 307, "pid": 2338710, "tid": 2379450, "ts": 6410534636887.851, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534636908.980, "dur": 8.335, + "args": { + "External id": 1418682,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636912.120, "dur": 4.626, + "args": { + "External id": 1418683,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534636920.046, "dur": 3.638, + "args": { + "External id": 1418684,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636921.815, "dur": 1.649, + "args": { + "External id": 1418685,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534636925.296, "dur": 4.211, + "args": { + "External id": 1418686,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534636926.898, "dur": 2.287, + "args": { + "External id": 1418687,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534636958.501, "dur": 333.330, + "args": { + "External id": 1418688,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 6591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534637053.112, "dur": 46.822, + "args": { + "External id": 1418689,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534637103.711, "dur": 3.384, + "args": { + "External id": 1418690,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534637108.865, "dur": 3.009, + "args": { + "External id": 1418691,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534637113.291, "dur": 6.659, + "args": { + "External id": 1418692,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534637172.615, "dur": 3.878, + "args": { + "External id": 1418693,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534637174.873, "dur": 1.514, + "args": { + "External id": 1418694,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534637180.962, "dur": 34.555, + "args": { + "External id": 1418695,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534637190.240, "dur": 1.352, + "args": { + "External id": 1418696,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534637217.634, "dur": 2.156, + "args": { + "External id": 1418697,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534637218.860, "dur": 0.825, + "args": { + "External id": 1418698,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534637221.145, "dur": 16.353, + "args": { + "External id": 1418699,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534637224.021, "dur": 0.759, + "args": { + "External id": 1418700,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534637307.380, "dur": 4.387, + "args": { + "External id": 1418701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534637315.235, "dur": 0.964, + "args": { + "External id": 1418702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534637318.340, "dur": 0.799, + "args": { + "External id": 1418703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534637367.100, "dur": 294.877, + "args": { + "External id": 1418704,"Record function id": 0, "Sequence number": 15109211, "Fwd thread id": 1, "Ev Idx": 6607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534637369.409, "dur": 283.111, + "args": { + "External id": 1418705,"Sequence number": 15109211, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6608 + } + }, + { + "ph": "f", "id": 308, "pid": 2338710, "tid": 2379450, "ts": 6410534637369.409, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534637394.731, "dur": 70.047, + "args": { + "External id": 1418706,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534637398.255, "dur": 4.440, + "args": { + "External id": 1418707,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534637404.354, "dur": 59.493, + "args": { + "External id": 1418708,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 6611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534637479.805, "dur": 7.271, + "args": { + "External id": 1418709,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534637482.647, "dur": 3.951, + "args": { + "External id": 1418710,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534637672.974, "dur": 193.767, + "args": { + "External id": 1418711,"Record function id": 0, "Sequence number": 15109210, "Fwd thread id": 1, "Ev Idx": 6614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534637675.320, "dur": 182.476, + "args": { + "External id": 1418712,"Sequence number": 15109210, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6615 + } + }, + { + "ph": "f", "id": 309, "pid": 2338710, "tid": 2379450, "ts": 6410534637675.320, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534637689.961, "dur": 51.831, + "args": { + "External id": 1418713,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534637693.698, "dur": 3.967, + "args": { + "External id": 1418714,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534637698.809, "dur": 42.327, + "args": { + "External id": 1418715,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 6618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534637750.269, "dur": 5.375, + "args": { + "External id": 1418716,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534637752.792, "dur": 2.488, + "args": { + "External id": 1418717,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637875.250, "dur": 16.804, + "args": { + "External id": 1418718,"Record function id": 0, "Sequence number": 15109209, "Fwd thread id": 1, "Ev Idx": 6621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637877.052, "dur": 11.434, + "args": { + "External id": 1418719,"Sequence number": 15109209, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6622 + } + }, + { + "ph": "f", "id": 310, "pid": 2338710, "tid": 2379450, "ts": 6410534637877.052, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534637880.635, "dur": 7.562, + "args": { + "External id": 1418720,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534637882.376, "dur": 5.572, + "args": { + "External id": 1418721,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637896.704, "dur": 10.306, + "args": { + "External id": 1418722,"Record function id": 0, "Sequence number": 15109208, "Fwd thread id": 1, "Ev Idx": 6625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637897.864, "dur": 6.579, + "args": { + "External id": 1418723,"Sequence number": 15109208, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6626 + } + }, + { + "ph": "f", "id": 311, "pid": 2338710, "tid": 2379450, "ts": 6410534637897.864, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534637899.944, "dur": 4.287, + "args": { + "External id": 1418724,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534637903.013, "dur": 1.095, + "args": { + "External id": 1418725,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637911.289, "dur": 7.426, + "args": { + "External id": 1418726,"Record function id": 0, "Sequence number": 15109207, "Fwd thread id": 1, "Ev Idx": 6629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637912.371, "dur": 4.057, + "args": { + "External id": 1418727,"Sequence number": 15109207, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6630 + } + }, + { + "ph": "f", "id": 312, "pid": 2338710, "tid": 2379450, "ts": 6410534637912.371, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534637913.902, "dur": 2.339, + "args": { + "External id": 1418728,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534637914.727, "dur": 1.366, + "args": { + "External id": 1418729,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637923.558, "dur": 10.523, + "args": { + "External id": 1418730,"Record function id": 0, "Sequence number": 15109206, "Fwd thread id": 1, "Ev Idx": 6633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637924.751, "dur": 6.124, + "args": { + "External id": 1418731,"Sequence number": 15109206, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6634 + } + }, + { + "ph": "f", "id": 313, "pid": 2338710, "tid": 2379450, "ts": 6410534637924.751, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534637926.234, "dur": 4.451, + "args": { + "External id": 1418732,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534637926.930, "dur": 3.639, + "args": { + "External id": 1418733,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637938.593, "dur": 248.973, + "args": { + "External id": 1418734,"Record function id": 0, "Sequence number": 15109205, "Fwd thread id": 1, "Ev Idx": 6637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534637941.825, "dur": 233.204, + "args": { + "External id": 1418735,"Sequence number": 15109205, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6638 + } + }, + { + "ph": "f", "id": 314, "pid": 2338710, "tid": 2379450, "ts": 6410534637941.825, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534637946.951, "dur": 7.429, + "args": { + "External id": 1418736,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534637948.847, "dur": 4.787, + "args": { + "External id": 1418737,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534637951.552, "dur": 1.683, + "args": { + "External id": 1418738,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534637956.371, "dur": 83.055, + "args": { + "External id": 1418739,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638041.308, "dur": 56.196, + "args": { + "External id": 1418740,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638042.382, "dur": 11.637, + "args": { + "External id": 1418741,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638050.862, "dur": 2.953, + "args": { + "External id": 1418742,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638101.951, "dur": 5.527, + "args": { + "External id": 1418743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638103.815, "dur": 3.085, + "args": { + "External id": 1418744,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638105.888, "dur": 0.872, + "args": { + "External id": 1418745,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534638108.658, "dur": 65.060, + "args": { + "External id": 1418746,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638197.251, "dur": 9.674, + "args": { + "External id": 1418747,"Record function id": 0, "Sequence number": 15109204, "Fwd thread id": 1, "Ev Idx": 6650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638198.753, "dur": 5.561, + "args": { + "External id": 1418748,"Sequence number": 15109204, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6651 + } + }, + { + "ph": "f", "id": 315, "pid": 2338710, "tid": 2379450, "ts": 6410534638198.753, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534638200.820, "dur": 3.224, + "args": { + "External id": 1418749,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534638201.927, "dur": 2.008, + "args": { + "External id": 1418750,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638213.669, "dur": 38.932, + "args": { + "External id": 1418751,"Record function id": 0, "Sequence number": 15109203, "Fwd thread id": 1, "Ev Idx": 6654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638214.931, "dur": 35.335, + "args": { + "External id": 1418752,"Sequence number": 15109203, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6655 + } + }, + { + "ph": "f", "id": 316, "pid": 2338710, "tid": 2379450, "ts": 6410534638214.931, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638245.808, "dur": 4.143, + "args": { + "External id": 1418753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638246.860, "dur": 2.469, + "args": { + "External id": 1418754,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638248.535, "dur": 0.634, + "args": { + "External id": 1418755,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534638260.017, "dur": 13.329, + "args": { + "External id": 1418756,"Record function id": 0, "Ev Idx": 6659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534638262.231, "dur": 10.153, + "args": { + "External id": 1418757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534638265.355, "dur": 6.500, + "args": { + "External id": 1418758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534638266.654, "dur": 5.052, + "args": { + "External id": 1418759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638277.788, "dur": 9.865, + "args": { + "External id": 1418760,"Record function id": 0, "Sequence number": 15109202, "Fwd thread id": 1, "Ev Idx": 6663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638279.324, "dur": 6.037, + "args": { + "External id": 1418761,"Sequence number": 15109202, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6664 + } + }, + { + "ph": "f", "id": 317, "pid": 2338710, "tid": 2379450, "ts": 6410534638279.324, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534638283.062, "dur": 2.084, + "args": { + "External id": 1418762,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534638284.032, "dur": 1.004, + "args": { + "External id": 1418763,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638292.049, "dur": 112.779, + "args": { + "External id": 1418764,"Record function id": 0, "Sequence number": 15109201, "Fwd thread id": 1, "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638293.106, "dur": 101.781, + "args": { + "External id": 1418765,"Sequence number": 15109201, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6668 + } + }, + { + "ph": "f", "id": 318, "pid": 2338710, "tid": 2379450, "ts": 6410534638293.106, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638296.919, "dur": 2.972, + "args": { + "External id": 1418766,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638297.456, "dur": 1.916, + "args": { + "External id": 1418767,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638298.760, "dur": 0.459, + "args": { + "External id": 1418768,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534638303.475, "dur": 36.169, + "args": { + "External id": 1418769,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638340.993, "dur": 3.588, + "args": { + "External id": 1418770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638341.679, "dur": 2.291, + "args": { + "External id": 1418771,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638343.189, "dur": 0.652, + "args": { + "External id": 1418772,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638346.082, "dur": 6.145, + "args": { + "External id": 1418773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638347.361, "dur": 4.253, + "args": { + "External id": 1418774,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638351.031, "dur": 0.460, + "args": { + "External id": 1418775,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534638353.030, "dur": 40.911, + "args": { + "External id": 1418776,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638410.596, "dur": 65.938, + "args": { + "External id": 1418777,"Record function id": 0, "Sequence number": 15109200, "Fwd thread id": 1, "Ev Idx": 6680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638411.678, "dur": 25.592, + "args": { + "External id": 1418778,"Sequence number": 15109200, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6681 + } + }, + { + "ph": "f", "id": 319, "pid": 2338710, "tid": 2379450, "ts": 6410534638411.678, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534638413.626, "dur": 23.434, + "args": { + "External id": 1418779,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534638432.432, "dur": 4.277, + "args": { + "External id": 1418780,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534638442.190, "dur": 30.722, + "args": { + "External id": 1418781,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638483.185, "dur": 11.721, + "args": { + "External id": 1418782,"Record function id": 0, "Sequence number": 15109199, "Fwd thread id": 1, "Ev Idx": 6685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638484.394, "dur": 7.888, + "args": { + "External id": 1418783,"Sequence number": 15109199, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6686 + } + }, + { + "ph": "f", "id": 320, "pid": 2338710, "tid": 2379450, "ts": 6410534638484.394, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638485.412, "dur": 6.618, + "args": { + "External id": 1418784,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638486.407, "dur": 4.909, + "args": { + "External id": 1418785,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638490.567, "dur": 0.563, + "args": { + "External id": 1418786,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534638499.975, "dur": 7.061, + "args": { + "External id": 1418787,"Record function id": 0, "Ev Idx": 6690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534638502.141, "dur": 4.206, + "args": { + "External id": 1418788,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534638503.625, "dur": 2.241, + "args": { + "External id": 1418789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534638504.212, "dur": 1.532, + "args": { + "External id": 1418790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638510.821, "dur": 8.199, + "args": { + "External id": 1418791,"Record function id": 0, "Sequence number": 15109198, "Fwd thread id": 1, "Ev Idx": 6694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638512.402, "dur": 3.774, + "args": { + "External id": 1418792,"Sequence number": 15109198, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6695 + } + }, + { + "ph": "f", "id": 321, "pid": 2338710, "tid": 2379450, "ts": 6410534638512.402, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534638513.541, "dur": 2.451, + "args": { + "External id": 1418793,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534638514.719, "dur": 1.155, + "args": { + "External id": 1418794,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638522.924, "dur": 120.398, + "args": { + "External id": 1418795,"Record function id": 0, "Sequence number": 15109197, "Fwd thread id": 1, "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638523.979, "dur": 108.404, + "args": { + "External id": 1418796,"Sequence number": 15109197, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6699 + } + }, + { + "ph": "f", "id": 322, "pid": 2338710, "tid": 2379450, "ts": 6410534638523.979, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638529.499, "dur": 3.108, + "args": { + "External id": 1418797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638530.060, "dur": 1.920, + "args": { + "External id": 1418798,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638531.342, "dur": 0.454, + "args": { + "External id": 1418799,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534638533.540, "dur": 44.598, + "args": { + "External id": 1418800,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638579.436, "dur": 6.462, + "args": { + "External id": 1418801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638580.129, "dur": 5.014, + "args": { + "External id": 1418802,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638583.964, "dur": 1.028, + "args": { + "External id": 1418803,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638587.453, "dur": 3.949, + "args": { + "External id": 1418804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638588.976, "dur": 1.900, + "args": { + "External id": 1418805,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638590.275, "dur": 0.501, + "args": { + "External id": 1418806,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534638591.925, "dur": 39.644, + "args": { + "External id": 1418807,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638648.781, "dur": 27.648, + "args": { + "External id": 1418808,"Record function id": 0, "Sequence number": 15109196, "Fwd thread id": 1, "Ev Idx": 6711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638649.872, "dur": 4.178, + "args": { + "External id": 1418809,"Sequence number": 15109196, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6712 + } + }, + { + "ph": "f", "id": 323, "pid": 2338710, "tid": 2379450, "ts": 6410534638649.872, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534638651.678, "dur": 2.188, + "args": { + "External id": 1418810,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534638652.596, "dur": 1.160, + "args": { + "External id": 1418811,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534638657.224, "dur": 16.706, + "args": { + "External id": 1418812,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638680.583, "dur": 11.843, + "args": { + "External id": 1418813,"Record function id": 0, "Sequence number": 15109195, "Fwd thread id": 1, "Ev Idx": 6716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534638681.739, "dur": 7.364, + "args": { + "External id": 1418814,"Sequence number": 15109195, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6717 + } + }, + { + "ph": "f", "id": 324, "pid": 2338710, "tid": 2379450, "ts": 6410534638681.739, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534638682.546, "dur": 6.305, + "args": { + "External id": 1418815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534638686.108, "dur": 2.141, + "args": { + "External id": 1418816,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638687.659, "dur": 0.442, + "args": { + "External id": 1418817,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534638697.356, "dur": 5.648, + "args": { + "External id": 1418818,"Record function id": 0, "Ev Idx": 6721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534638699.013, "dur": 3.420, + "args": { + "External id": 1418819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534638700.157, "dur": 1.899, + "args": { + "External id": 1418820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534638700.672, "dur": 1.295, + "args": { + "External id": 1418821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534638708.623, "dur": 473.721, + "args": { + "External id": 1418822,"Record function id": 0, "Sequence number": 15109194, "Fwd thread id": 1, "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534638710.367, "dur": 433.061, + "args": { + "External id": 1418823,"Sequence number": 15109194, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6726 + } + }, + { + "ph": "f", "id": 325, "pid": 2338710, "tid": 2379450, "ts": 6410534638710.367, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534638755.391, "dur": 2.250, + "args": { + "External id": 1418824,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534638756.337, "dur": 1.121, + "args": { + "External id": 1418825,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534638776.979, "dur": 4.752, + "args": { + "External id": 1418826,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534638793.186, "dur": 2.581, + "args": { + "External id": 1418827,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534638975.376, "dur": 2.101, + "args": { + "External id": 1418828,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534638982.139, "dur": 41.420, + "args": { + "External id": 1418829,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534638996.769, "dur": 1.046, + "args": { + "External id": 1418830,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534639030.010, "dur": 80.500, + "args": { + "External id": 1418831,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534639032.145, "dur": 77.901, + "args": { + "External id": 1418832,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639036.798, "dur": 5.076, + "args": { + "External id": 1418833,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534639046.083, "dur": 62.843, + "args": { + "External id": 1418834,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534639119.064, "dur": 4.498, + "args": { + "External id": 1418835,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639121.181, "dur": 2.242, + "args": { + "External id": 1418836,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534639132.738, "dur": 2.272, + "args": { + "External id": 1418837,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639133.961, "dur": 0.935, + "args": { + "External id": 1418838,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534639157.080, "dur": 20.895, + "args": { + "External id": 1418839,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534639200.495, "dur": 10.271, + "args": { + "External id": 1418840,"Record function id": 0, "Ev Idx": 6743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534639202.924, "dur": 6.949, + "args": { + "External id": 1418841,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534639205.297, "dur": 3.241, + "args": { + "External id": 1418842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534639206.351, "dur": 2.026, + "args": { + "External id": 1418843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639215.482, "dur": 8.069, + "args": { + "External id": 1418844,"Record function id": 0, "Sequence number": 15109193, "Fwd thread id": 1, "Ev Idx": 6747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639217.292, "dur": 1.991, + "args": { + "External id": 1418845,"Sequence number": 15109193, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6748 + } + }, + { + "ph": "f", "id": 326, "pid": 2338710, "tid": 2379450, "ts": 6410534639217.292, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534639227.978, "dur": 508.350, + "args": { + "External id": 1418846,"Record function id": 0, "Sequence number": 15109192, "Fwd thread id": 1, "Ev Idx": 6749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534639233.102, "dur": 487.443, + "args": { + "External id": 1418847,"Sequence number": 15109192, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6750 + } + }, + { + "ph": "f", "id": 327, "pid": 2338710, "tid": 2379450, "ts": 6410534639233.102, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534639271.043, "dur": 9.474, + "args": { + "External id": 1418848,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534639276.731, "dur": 3.480, + "args": { + "External id": 1418849,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 6752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534639286.241, "dur": 6.009, + "args": { + "External id": 1418850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534639287.715, "dur": 3.621, + "args": { + "External id": 1418851,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639290.056, "dur": 1.020, + "args": { + "External id": 1418852,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2379450, + "ts": 6410534639296.343, "dur": 105.341, + "args": { + "External id": 1418853,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 6756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534639297.483, "dur": 7.784, + "args": { + "External id": 1418854,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 6757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534639298.330, "dur": 6.335, + "args": { + "External id": 1418855,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639302.156, "dur": 2.295, + "args": { + "External id": 1418856,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2379450, + "ts": 6410534639306.524, "dur": 94.621, + "args": { + "External id": 1418857,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534639308.104, "dur": 92.124, + "args": { + "External id": 1418858,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534639406.395, "dur": 3.589, + "args": { + "External id": 1418859,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 6762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639408.221, "dur": 1.590, + "args": { + "External id": 1418860,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534639467.360, "dur": 6.111, + "args": { + "External id": 1418861,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534639475.238, "dur": 7.470, + "args": { + "External id": 1418862,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534639486.693, "dur": 2.473, + "args": { + "External id": 1418863,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534639525.834, "dur": 3.382, + "args": { + "External id": 1418864,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639526.824, "dur": 2.180, + "args": { + "External id": 1418865,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338710, "tid": 2379450, + "ts": 6410534639554.769, "dur": 143.896, + "args": { + "External id": 1418866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 6769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410534639562.700, "dur": 6.458, + "args": { + "External id": 1418867,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639567.107, "dur": 1.079, + "args": { + "External id": 1418868,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534639571.275, "dur": 5.352, + "args": { + "External id": 1418869,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 6772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639575.195, "dur": 0.749, + "args": { + "External id": 1418870,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 6773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410534639580.874, "dur": 3.462, + "args": { + "External id": 1418871,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639583.206, "dur": 0.740, + "args": { + "External id": 1418872,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534639585.407, "dur": 3.577, + "args": { + "External id": 1418873,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639587.881, "dur": 0.515, + "args": { + "External id": 1418874,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 6777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534639594.083, "dur": 5.543, + "args": { + "External id": 1418875,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 6778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639598.525, "dur": 0.701, + "args": { + "External id": 1418876,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 6779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534639601.148, "dur": 9.620, + "args": { + "External id": 1418877,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 6780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534639606.211, "dur": 4.371, + "args": { + "External id": 1418878,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 6781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534639612.165, "dur": 2.645, + "args": { + "External id": 1418879,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 6782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639614.068, "dur": 0.395, + "args": { + "External id": 1418880,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 6783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534639615.771, "dur": 4.662, + "args": { + "External id": 1418881,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639618.482, "dur": 1.832, + "args": { + "External id": 1418882,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410534639622.034, "dur": 63.946, + "args": { + "External id": 1418883,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 6786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639688.419, "dur": 1.182, + "args": { + "External id": 1418884,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 6787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534639690.494, "dur": 3.749, + "args": { + "External id": 1418885,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 6788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639692.985, "dur": 0.424, + "args": { + "External id": 1418886,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 6789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639696.552, "dur": 0.939, + "args": { + "External id": 1418887,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 6790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534639749.594, "dur": 10.678, + "args": { + "External id": 1418888,"Record function id": 0, "Ev Idx": 6791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534639751.670, "dur": 7.762, + "args": { + "External id": 1418889,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534639754.221, "dur": 3.981, + "args": { + "External id": 1418890,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534639755.258, "dur": 2.778, + "args": { + "External id": 1418891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639765.106, "dur": 11.886, + "args": { + "External id": 1418892,"Record function id": 0, "Sequence number": 15109191, "Fwd thread id": 1, "Ev Idx": 6795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639766.558, "dur": 7.152, + "args": { + "External id": 1418893,"Sequence number": 15109191, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6796 + } + }, + { + "ph": "f", "id": 328, "pid": 2338710, "tid": 2379450, "ts": 6410534639766.558, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534639768.925, "dur": 4.480, + "args": { + "External id": 1418894,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639772.309, "dur": 0.989, + "args": { + "External id": 1418895,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639781.506, "dur": 127.134, + "args": { + "External id": 1418896,"Record function id": 0, "Sequence number": 15109190, "Fwd thread id": 1, "Ev Idx": 6799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639782.495, "dur": 118.451, + "args": { + "External id": 1418897,"Sequence number": 15109190, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6800 + } + }, + { + "ph": "f", "id": 329, "pid": 2338710, "tid": 2379450, "ts": 6410534639782.495, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534639787.239, "dur": 6.733, + "args": { + "External id": 1418898,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534639788.567, "dur": 4.720, + "args": { + "External id": 1418899,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639790.159, "dur": 2.978, + "args": { + "External id": 1418900,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534639797.214, "dur": 47.666, + "args": { + "External id": 1418901,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534639846.681, "dur": 5.108, + "args": { + "External id": 1418902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534639847.620, "dur": 3.493, + "args": { + "External id": 1418903,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639849.316, "dur": 1.549, + "args": { + "External id": 1418904,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534639854.141, "dur": 6.618, + "args": { + "External id": 1418905,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534639855.633, "dur": 4.436, + "args": { + "External id": 1418906,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639859.524, "dur": 0.423, + "args": { + "External id": 1418907,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534639861.381, "dur": 38.535, + "args": { + "External id": 1418908,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639914.287, "dur": 7.960, + "args": { + "External id": 1418909,"Record function id": 0, "Sequence number": 15109189, "Fwd thread id": 1, "Ev Idx": 6812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639915.483, "dur": 5.057, + "args": { + "External id": 1418910,"Sequence number": 15109189, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6813 + } + }, + { + "ph": "f", "id": 330, "pid": 2338710, "tid": 2379450, "ts": 6410534639915.483, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534639917.686, "dur": 2.634, + "args": { + "External id": 1418911,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639918.677, "dur": 1.470, + "args": { + "External id": 1418912,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639926.775, "dur": 11.199, + "args": { + "External id": 1418913,"Record function id": 0, "Sequence number": 15109188, "Fwd thread id": 1, "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639928.185, "dur": 6.842, + "args": { + "External id": 1418914,"Sequence number": 15109188, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6817 + } + }, + { + "ph": "f", "id": 331, "pid": 2338710, "tid": 2379450, "ts": 6410534639928.185, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534639929.270, "dur": 5.461, + "args": { + "External id": 1418915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534639930.047, "dur": 4.107, + "args": { + "External id": 1418916,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639933.485, "dur": 0.550, + "args": { + "External id": 1418917,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534639942.985, "dur": 8.228, + "args": { + "External id": 1418918,"Record function id": 0, "Ev Idx": 6821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534639944.646, "dur": 5.986, + "args": { + "External id": 1418919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534639945.692, "dur": 4.694, + "args": { + "External id": 1418920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534639946.310, "dur": 3.965, + "args": { + "External id": 1418921,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639955.239, "dur": 7.415, + "args": { + "External id": 1418922,"Record function id": 0, "Sequence number": 15109187, "Fwd thread id": 1, "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639956.583, "dur": 3.714, + "args": { + "External id": 1418923,"Sequence number": 15109187, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6826 + } + }, + { + "ph": "f", "id": 332, "pid": 2338710, "tid": 2379450, "ts": 6410534639956.583, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534639958.053, "dur": 2.069, + "args": { + "External id": 1418924,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534639959.170, "dur": 0.799, + "args": { + "External id": 1418925,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639966.672, "dur": 157.253, + "args": { + "External id": 1418926,"Record function id": 0, "Sequence number": 15109186, "Fwd thread id": 1, "Ev Idx": 6829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534639967.932, "dur": 143.188, + "args": { + "External id": 1418927,"Sequence number": 15109186, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6830 + } + }, + { + "ph": "f", "id": 333, "pid": 2338710, "tid": 2379450, "ts": 6410534639967.932, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534639973.347, "dur": 3.283, + "args": { + "External id": 1418928,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534639974.065, "dur": 2.014, + "args": { + "External id": 1418929,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534639975.327, "dur": 0.636, + "args": { + "External id": 1418930,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534639977.344, "dur": 37.044, + "args": { + "External id": 1418931,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534640015.794, "dur": 6.792, + "args": { + "External id": 1418932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534640016.550, "dur": 5.383, + "args": { + "External id": 1418933,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640020.633, "dur": 1.152, + "args": { + "External id": 1418934,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534640023.886, "dur": 4.270, + "args": { + "External id": 1418935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534640025.511, "dur": 1.982, + "args": { + "External id": 1418936,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640026.949, "dur": 0.463, + "args": { + "External id": 1418937,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534640028.774, "dur": 80.414, + "args": { + "External id": 1418938,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640132.984, "dur": 42.195, + "args": { + "External id": 1418939,"Record function id": 0, "Sequence number": 15109185, "Fwd thread id": 1, "Ev Idx": 6842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640134.503, "dur": 6.253, + "args": { + "External id": 1418940,"Sequence number": 15109185, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6843 + } + }, + { + "ph": "f", "id": 334, "pid": 2338710, "tid": 2379450, "ts": 6410534640134.503, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534640137.321, "dur": 3.271, + "args": { + "External id": 1418941,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640138.494, "dur": 1.982, + "args": { + "External id": 1418942,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534640144.605, "dur": 27.009, + "args": { + "External id": 1418943,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640179.698, "dur": 12.542, + "args": { + "External id": 1418944,"Record function id": 0, "Sequence number": 15109184, "Fwd thread id": 1, "Ev Idx": 6847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640180.806, "dur": 8.543, + "args": { + "External id": 1418945,"Sequence number": 15109184, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6848 + } + }, + { + "ph": "f", "id": 335, "pid": 2338710, "tid": 2379450, "ts": 6410534640180.806, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534640184.054, "dur": 5.029, + "args": { + "External id": 1418946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534640185.086, "dur": 3.231, + "args": { + "External id": 1418947,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640187.527, "dur": 0.674, + "args": { + "External id": 1418948,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534640197.232, "dur": 6.931, + "args": { + "External id": 1418949,"Record function id": 0, "Ev Idx": 6852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534640199.279, "dur": 4.242, + "args": { + "External id": 1418950,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534640200.751, "dur": 2.281, + "args": { + "External id": 1418951,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534640201.426, "dur": 1.523, + "args": { + "External id": 1418952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534640209.400, "dur": 499.247, + "args": { + "External id": 1418953,"Record function id": 0, "Sequence number": 15109183, "Fwd thread id": 1, "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534640211.066, "dur": 457.901, + "args": { + "External id": 1418954,"Sequence number": 15109183, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 6857 + } + }, + { + "ph": "f", "id": 336, "pid": 2338710, "tid": 2379450, "ts": 6410534640211.066, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2379450, + "ts": 6410534640239.293, "dur": 42.913, + "args": { + "External id": 1418955,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534640241.161, "dur": 40.796, + "args": { + "External id": 1418956,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534640244.341, "dur": 12.055, + "args": { + "External id": 1418957,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 6860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534640252.443, "dur": 3.176, + "args": { + "External id": 1418958,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534640258.165, "dur": 23.162, + "args": { + "External id": 1418959,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534640295.460, "dur": 5.096, + "args": { + "External id": 1418960,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640298.967, "dur": 1.399, + "args": { + "External id": 1418961,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534640304.864, "dur": 2.522, + "args": { + "External id": 1418962,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640306.320, "dur": 0.955, + "args": { + "External id": 1418963,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534640320.742, "dur": 2.377, + "args": { + "External id": 1418964,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534640338.074, "dur": 3.268, + "args": { + "External id": 1418965,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640543.456, "dur": 7.784, + "args": { + "External id": 1418966,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534640556.368, "dur": 37.773, + "args": { + "External id": 1418967,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640568.153, "dur": 0.945, + "args": { + "External id": 1418968,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534640600.886, "dur": 31.338, + "args": { + "External id": 1418969,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534640603.053, "dur": 28.833, + "args": { + "External id": 1418970,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640607.816, "dur": 5.206, + "args": { + "External id": 1418971,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534640614.612, "dur": 16.644, + "args": { + "External id": 1418972,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534640639.678, "dur": 2.718, + "args": { + "External id": 1418973,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640641.089, "dur": 1.118, + "args": { + "External id": 1418974,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534640650.840, "dur": 2.747, + "args": { + "External id": 1418975,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640652.212, "dur": 1.224, + "args": { + "External id": 1418976,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534640656.104, "dur": 2.628, + "args": { + "External id": 1418977,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640657.212, "dur": 1.387, + "args": { + "External id": 1418978,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534640688.547, "dur": 18.141, + "args": { + "External id": 1418979,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534640722.660, "dur": 12.559, + "args": { + "External id": 1418980,"Record function id": 0, "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534640725.514, "dur": 8.736, + "args": { + "External id": 1418981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534640727.980, "dur": 5.277, + "args": { + "External id": 1418982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534640731.367, "dur": 1.761, + "args": { + "External id": 1418983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640739.376, "dur": 8.960, + "args": { + "External id": 1418984,"Record function id": 0, "Sequence number": 15109182, "Fwd thread id": 1, "Ev Idx": 6887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640740.731, "dur": 4.524, + "args": { + "External id": 1418985,"Sequence number": 15109182, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6888 + } + }, + { + "ph": "f", "id": 337, "pid": 2338710, "tid": 2379450, "ts": 6410534640740.731, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534640742.595, "dur": 2.451, + "args": { + "External id": 1418986,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640743.672, "dur": 1.260, + "args": { + "External id": 1418987,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640752.813, "dur": 197.377, + "args": { + "External id": 1418988,"Record function id": 0, "Sequence number": 15109181, "Fwd thread id": 1, "Ev Idx": 6891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640753.956, "dur": 187.495, + "args": { + "External id": 1418989,"Sequence number": 15109181, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6892 + } + }, + { + "ph": "f", "id": 338, "pid": 2338710, "tid": 2379450, "ts": 6410534640753.956, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534640758.650, "dur": 7.215, + "args": { + "External id": 1418990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534640760.272, "dur": 4.965, + "args": { + "External id": 1418991,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640764.056, "dur": 0.931, + "args": { + "External id": 1418992,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534640767.174, "dur": 95.660, + "args": { + "External id": 1418993,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534640864.436, "dur": 6.311, + "args": { + "External id": 1418994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534640865.234, "dur": 4.697, + "args": { + "External id": 1418995,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640867.159, "dur": 2.561, + "args": { + "External id": 1418996,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534640872.502, "dur": 6.424, + "args": { + "External id": 1418997,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534640873.914, "dur": 4.523, + "args": { + "External id": 1418998,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640877.780, "dur": 0.544, + "args": { + "External id": 1418999,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534640879.663, "dur": 60.851, + "args": { + "External id": 1419000,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640956.104, "dur": 10.109, + "args": { + "External id": 1419001,"Record function id": 0, "Sequence number": 15109180, "Fwd thread id": 1, "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640957.419, "dur": 5.633, + "args": { + "External id": 1419002,"Sequence number": 15109180, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6905 + } + }, + { + "ph": "f", "id": 339, "pid": 2338710, "tid": 2379450, "ts": 6410534640957.419, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534640959.641, "dur": 3.231, + "args": { + "External id": 1419003,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534640961.341, "dur": 1.390, + "args": { + "External id": 1419004,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640969.952, "dur": 9.299, + "args": { + "External id": 1419005,"Record function id": 0, "Sequence number": 15109179, "Fwd thread id": 1, "Ev Idx": 6908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640971.114, "dur": 5.366, + "args": { + "External id": 1419006,"Sequence number": 15109179, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6909 + } + }, + { + "ph": "f", "id": 340, "pid": 2338710, "tid": 2379450, "ts": 6410534640971.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534640972.323, "dur": 3.883, + "args": { + "External id": 1419007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534640973.043, "dur": 2.575, + "args": { + "External id": 1419008,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534640974.783, "dur": 0.735, + "args": { + "External id": 1419009,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534640984.079, "dur": 11.590, + "args": { + "External id": 1419010,"Record function id": 0, "Ev Idx": 6913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534640985.699, "dur": 9.259, + "args": { + "External id": 1419011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534640986.825, "dur": 7.695, + "args": { + "External id": 1419012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534640989.745, "dur": 4.592, + "args": { + "External id": 1419013,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534640999.502, "dur": 7.793, + "args": { + "External id": 1419014,"Record function id": 0, "Sequence number": 15109178, "Fwd thread id": 1, "Ev Idx": 6917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534641000.553, "dur": 4.187, + "args": { + "External id": 1419015,"Sequence number": 15109178, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6918 + } + }, + { + "ph": "f", "id": 341, "pid": 2338710, "tid": 2379450, "ts": 6410534641000.553, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534641002.010, "dur": 2.566, + "args": { + "External id": 1419016,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534641003.021, "dur": 1.380, + "args": { + "External id": 1419017,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534641013.189, "dur": 506.794, + "args": { + "External id": 1419018,"Record function id": 0, "Sequence number": 15109177, "Fwd thread id": 1, "Ev Idx": 6921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534641014.601, "dur": 478.627, + "args": { + "External id": 1419019,"Sequence number": 15109177, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6922 + } + }, + { + "ph": "f", "id": 342, "pid": 2338710, "tid": 2379450, "ts": 6410534641014.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534641032.519, "dur": 7.680, + "args": { + "External id": 1419020,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641036.067, "dur": 3.615, + "args": { + "External id": 1419021,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534641042.579, "dur": 4.867, + "args": { + "External id": 1419022,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641045.033, "dur": 2.150, + "args": { + "External id": 1419023,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534641049.214, "dur": 4.560, + "args": { + "External id": 1419024,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641050.778, "dur": 2.776, + "args": { + "External id": 1419025,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534641124.781, "dur": 336.111, + "args": { + "External id": 1419026,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 6929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534641219.665, "dur": 6.705, + "args": { + "External id": 1419027,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534641229.076, "dur": 3.343, + "args": { + "External id": 1419028,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534641234.021, "dur": 2.928, + "args": { + "External id": 1419029,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534641238.071, "dur": 2.522, + "args": { + "External id": 1419030,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534641327.888, "dur": 3.605, + "args": { + "External id": 1419031,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534641329.426, "dur": 1.943, + "args": { + "External id": 1419032,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534641333.725, "dur": 32.820, + "args": { + "External id": 1419033,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641342.140, "dur": 1.163, + "args": { + "External id": 1419034,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534641368.235, "dur": 2.961, + "args": { + "External id": 1419035,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534641370.416, "dur": 0.669, + "args": { + "External id": 1419036,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534641374.198, "dur": 19.243, + "args": { + "External id": 1419037,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641377.143, "dur": 0.455, + "args": { + "External id": 1419038,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534641477.825, "dur": 4.550, + "args": { + "External id": 1419039,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534641485.987, "dur": 0.887, + "args": { + "External id": 1419040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534641489.201, "dur": 0.586, + "args": { + "External id": 1419041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534641532.989, "dur": 275.410, + "args": { + "External id": 1419042,"Record function id": 0, "Sequence number": 15109176, "Fwd thread id": 1, "Ev Idx": 6945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534641535.129, "dur": 265.149, + "args": { + "External id": 1419043,"Sequence number": 15109176, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6946 + } + }, + { + "ph": "f", "id": 343, "pid": 2338710, "tid": 2379450, "ts": 6410534641535.129, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534641559.712, "dur": 58.588, + "args": { + "External id": 1419044,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641564.309, "dur": 5.447, + "args": { + "External id": 1419045,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534641571.515, "dur": 46.167, + "args": { + "External id": 1419046,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 6949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534641630.469, "dur": 5.767, + "args": { + "External id": 1419047,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641633.168, "dur": 2.608, + "args": { + "External id": 1419048,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534641817.474, "dur": 197.208, + "args": { + "External id": 1419049,"Record function id": 0, "Sequence number": 15109175, "Fwd thread id": 1, "Ev Idx": 6952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534641819.524, "dur": 186.797, + "args": { + "External id": 1419050,"Sequence number": 15109175, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6953 + } + }, + { + "ph": "f", "id": 344, "pid": 2338710, "tid": 2379450, "ts": 6410534641819.524, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534641833.382, "dur": 57.737, + "args": { + "External id": 1419051,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641840.716, "dur": 5.811, + "args": { + "External id": 1419052,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534641850.710, "dur": 39.686, + "args": { + "External id": 1419053,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 6956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534641899.982, "dur": 5.941, + "args": { + "External id": 1419054,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534641902.359, "dur": 3.166, + "args": { + "External id": 1419055,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642022.368, "dur": 17.588, + "args": { + "External id": 1419056,"Record function id": 0, "Sequence number": 15109174, "Fwd thread id": 1, "Ev Idx": 6959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642023.917, "dur": 11.937, + "args": { + "External id": 1419057,"Sequence number": 15109174, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6960 + } + }, + { + "ph": "f", "id": 345, "pid": 2338710, "tid": 2379450, "ts": 6410534642023.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642027.189, "dur": 8.385, + "args": { + "External id": 1419058,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642028.966, "dur": 6.435, + "args": { + "External id": 1419059,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642044.038, "dur": 9.420, + "args": { + "External id": 1419060,"Record function id": 0, "Sequence number": 15109173, "Fwd thread id": 1, "Ev Idx": 6963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642045.527, "dur": 4.696, + "args": { + "External id": 1419061,"Sequence number": 15109173, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6964 + } + }, + { + "ph": "f", "id": 346, "pid": 2338710, "tid": 2379450, "ts": 6410534642045.527, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642047.413, "dur": 2.659, + "args": { + "External id": 1419062,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642048.715, "dur": 1.209, + "args": { + "External id": 1419063,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642099.823, "dur": 12.739, + "args": { + "External id": 1419064,"Record function id": 0, "Sequence number": 15109172, "Fwd thread id": 1, "Ev Idx": 6967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642101.405, "dur": 8.515, + "args": { + "External id": 1419065,"Sequence number": 15109172, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6968 + } + }, + { + "ph": "f", "id": 347, "pid": 2338710, "tid": 2379450, "ts": 6410534642101.405, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642104.034, "dur": 5.689, + "args": { + "External id": 1419066,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642107.608, "dur": 1.872, + "args": { + "External id": 1419067,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642116.906, "dur": 8.511, + "args": { + "External id": 1419068,"Record function id": 0, "Sequence number": 15109171, "Fwd thread id": 1, "Ev Idx": 6971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642118.369, "dur": 3.465, + "args": { + "External id": 1419069,"Sequence number": 15109171, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6972 + } + }, + { + "ph": "f", "id": 348, "pid": 2338710, "tid": 2379450, "ts": 6410534642118.369, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642119.812, "dur": 1.869, + "args": { + "External id": 1419070,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642120.507, "dur": 1.015, + "args": { + "External id": 1419071,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642129.905, "dur": 196.332, + "args": { + "External id": 1419072,"Record function id": 0, "Sequence number": 15109170, "Fwd thread id": 1, "Ev Idx": 6975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642130.983, "dur": 183.298, + "args": { + "External id": 1419073,"Sequence number": 15109170, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6976 + } + }, + { + "ph": "f", "id": 349, "pid": 2338710, "tid": 2379450, "ts": 6410534642130.983, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642136.332, "dur": 10.324, + "args": { + "External id": 1419074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642138.543, "dur": 7.242, + "args": { + "External id": 1419075,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642143.676, "dur": 1.787, + "args": { + "External id": 1419076,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534642148.390, "dur": 90.692, + "args": { + "External id": 1419077,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642240.902, "dur": 7.951, + "args": { + "External id": 1419078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642241.859, "dur": 6.084, + "args": { + "External id": 1419079,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642244.128, "dur": 3.655, + "args": { + "External id": 1419080,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642251.252, "dur": 6.678, + "args": { + "External id": 1419081,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642253.032, "dur": 4.369, + "args": { + "External id": 1419082,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642256.663, "dur": 0.649, + "args": { + "External id": 1419083,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534642258.622, "dur": 54.604, + "args": { + "External id": 1419084,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642332.890, "dur": 10.007, + "args": { + "External id": 1419085,"Record function id": 0, "Sequence number": 15109169, "Fwd thread id": 1, "Ev Idx": 6988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642334.057, "dur": 6.077, + "args": { + "External id": 1419086,"Sequence number": 15109169, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6989 + } + }, + { + "ph": "f", "id": 350, "pid": 2338710, "tid": 2379450, "ts": 6410534642334.057, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642336.715, "dur": 3.232, + "args": { + "External id": 1419087,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642338.128, "dur": 1.648, + "args": { + "External id": 1419088,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642346.967, "dur": 11.994, + "args": { + "External id": 1419089,"Record function id": 0, "Sequence number": 15109168, "Fwd thread id": 1, "Ev Idx": 6992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642348.158, "dur": 8.458, + "args": { + "External id": 1419090,"Sequence number": 15109168, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6993 + } + }, + { + "ph": "f", "id": 351, "pid": 2338710, "tid": 2379450, "ts": 6410534642348.158, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642349.452, "dur": 6.923, + "args": { + "External id": 1419091,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642350.168, "dur": 5.589, + "args": { + "External id": 1419092,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642355.092, "dur": 0.550, + "args": { + "External id": 1419093,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534642366.260, "dur": 11.444, + "args": { + "External id": 1419094,"Record function id": 0, "Ev Idx": 6997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534642368.452, "dur": 8.406, + "args": { + "External id": 1419095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534642371.498, "dur": 4.879, + "args": { + "External id": 1419096,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534642373.197, "dur": 3.074, + "args": { + "External id": 1419097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642382.042, "dur": 8.379, + "args": { + "External id": 1419098,"Record function id": 0, "Sequence number": 15109167, "Fwd thread id": 1, "Ev Idx": 7001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642383.704, "dur": 3.807, + "args": { + "External id": 1419099,"Sequence number": 15109167, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 7002 + } + }, + { + "ph": "f", "id": 352, "pid": 2338710, "tid": 2379450, "ts": 6410534642383.704, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642385.357, "dur": 2.006, + "args": { + "External id": 1419100,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642386.258, "dur": 0.994, + "args": { + "External id": 1419101,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642394.530, "dur": 138.247, + "args": { + "External id": 1419102,"Record function id": 0, "Sequence number": 15109166, "Fwd thread id": 1, "Ev Idx": 7005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642397.832, "dur": 124.978, + "args": { + "External id": 1419103,"Sequence number": 15109166, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7006 + } + }, + { + "ph": "f", "id": 353, "pid": 2338710, "tid": 2379450, "ts": 6410534642397.832, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642400.938, "dur": 3.407, + "args": { + "External id": 1419104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642401.875, "dur": 1.910, + "args": { + "External id": 1419105,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 7008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642403.067, "dur": 0.566, + "args": { + "External id": 1419106,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 7009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534642405.386, "dur": 56.031, + "args": { + "External id": 1419107,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 7010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642464.010, "dur": 9.037, + "args": { + "External id": 1419108,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642465.345, "dur": 6.778, + "args": { + "External id": 1419109,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 7012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642470.299, "dur": 1.678, + "args": { + "External id": 1419110,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 7013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642474.802, "dur": 3.865, + "args": { + "External id": 1419111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642476.157, "dur": 1.832, + "args": { + "External id": 1419112,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642477.413, "dur": 0.476, + "args": { + "External id": 1419113,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534642479.280, "dur": 42.536, + "args": { + "External id": 1419114,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 7017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642540.524, "dur": 40.548, + "args": { + "External id": 1419115,"Record function id": 0, "Sequence number": 15109165, "Fwd thread id": 1, "Ev Idx": 7018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642541.882, "dur": 5.160, + "args": { + "External id": 1419116,"Sequence number": 15109165, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7019 + } + }, + { + "ph": "f", "id": 354, "pid": 2338710, "tid": 2379450, "ts": 6410534642541.882, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642543.951, "dur": 2.910, + "args": { + "External id": 1419117,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642545.322, "dur": 1.380, + "args": { + "External id": 1419118,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534642550.872, "dur": 27.417, + "args": { + "External id": 1419119,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642588.012, "dur": 8.948, + "args": { + "External id": 1419120,"Record function id": 0, "Sequence number": 15109164, "Fwd thread id": 1, "Ev Idx": 7023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642589.562, "dur": 5.531, + "args": { + "External id": 1419121,"Sequence number": 15109164, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7024 + } + }, + { + "ph": "f", "id": 355, "pid": 2338710, "tid": 2379450, "ts": 6410534642589.562, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642590.504, "dur": 4.352, + "args": { + "External id": 1419122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642591.553, "dur": 2.671, + "args": { + "External id": 1419123,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642593.354, "dur": 0.711, + "args": { + "External id": 1419124,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534642602.286, "dur": 9.042, + "args": { + "External id": 1419125,"Record function id": 0, "Ev Idx": 7028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534642603.863, "dur": 6.889, + "args": { + "External id": 1419126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534642605.702, "dur": 4.585, + "args": { + "External id": 1419127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534642606.329, "dur": 3.848, + "args": { + "External id": 1419128,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642615.382, "dur": 10.059, + "args": { + "External id": 1419129,"Record function id": 0, "Sequence number": 15109163, "Fwd thread id": 1, "Ev Idx": 7032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642616.730, "dur": 6.294, + "args": { + "External id": 1419130,"Sequence number": 15109163, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7033 + } + }, + { + "ph": "f", "id": 356, "pid": 2338710, "tid": 2379450, "ts": 6410534642616.730, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642618.259, "dur": 4.599, + "args": { + "External id": 1419131,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642621.582, "dur": 1.148, + "args": { + "External id": 1419132,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642629.735, "dur": 113.997, + "args": { + "External id": 1419133,"Record function id": 0, "Sequence number": 15109162, "Fwd thread id": 1, "Ev Idx": 7036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642630.742, "dur": 102.795, + "args": { + "External id": 1419134,"Sequence number": 15109162, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7037 + } + }, + { + "ph": "f", "id": 357, "pid": 2338710, "tid": 2379450, "ts": 6410534642630.742, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642633.746, "dur": 3.264, + "args": { + "External id": 1419135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642634.255, "dur": 2.217, + "args": { + "External id": 1419136,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 7039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642635.595, "dur": 0.742, + "args": { + "External id": 1419137,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 7040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534642637.891, "dur": 40.690, + "args": { + "External id": 1419138,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 7041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642682.587, "dur": 3.921, + "args": { + "External id": 1419139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642683.138, "dur": 2.742, + "args": { + "External id": 1419140,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642684.604, "dur": 1.140, + "args": { + "External id": 1419141,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642687.769, "dur": 4.559, + "args": { + "External id": 1419142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642689.355, "dur": 2.230, + "args": { + "External id": 1419143,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642690.874, "dur": 0.627, + "args": { + "External id": 1419144,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534642695.246, "dur": 37.411, + "args": { + "External id": 1419145,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 7048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642749.684, "dur": 30.593, + "args": { + "External id": 1419146,"Record function id": 0, "Sequence number": 15109161, "Fwd thread id": 1, "Ev Idx": 7049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642751.284, "dur": 5.140, + "args": { + "External id": 1419147,"Sequence number": 15109161, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7050 + } + }, + { + "ph": "f", "id": 358, "pid": 2338710, "tid": 2379450, "ts": 6410534642751.284, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642753.331, "dur": 2.925, + "args": { + "External id": 1419148,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642754.655, "dur": 1.476, + "args": { + "External id": 1419149,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534642759.501, "dur": 18.087, + "args": { + "External id": 1419150,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642784.704, "dur": 12.820, + "args": { + "External id": 1419151,"Record function id": 0, "Sequence number": 15109160, "Fwd thread id": 1, "Ev Idx": 7054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534642785.661, "dur": 8.836, + "args": { + "External id": 1419152,"Sequence number": 15109160, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7055 + } + }, + { + "ph": "f", "id": 359, "pid": 2338710, "tid": 2379450, "ts": 6410534642785.661, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534642786.923, "dur": 7.339, + "args": { + "External id": 1419153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534642787.811, "dur": 5.745, + "args": { + "External id": 1419154,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534642790.366, "dur": 3.018, + "args": { + "External id": 1419155,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534642802.273, "dur": 6.924, + "args": { + "External id": 1419156,"Record function id": 0, "Ev Idx": 7059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534642804.220, "dur": 4.419, + "args": { + "External id": 1419157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534642805.788, "dur": 2.343, + "args": { + "External id": 1419158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534642806.734, "dur": 1.278, + "args": { + "External id": 1419159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534642814.392, "dur": 468.826, + "args": { + "External id": 1419160,"Record function id": 0, "Sequence number": 15109159, "Fwd thread id": 1, "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534642815.977, "dur": 430.421, + "args": { + "External id": 1419161,"Sequence number": 15109159, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7064 + } + }, + { + "ph": "f", "id": 360, "pid": 2338710, "tid": 2379450, "ts": 6410534642815.977, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534642858.566, "dur": 2.779, + "args": { + "External id": 1419162,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534642859.848, "dur": 1.330, + "args": { + "External id": 1419163,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534642878.367, "dur": 4.579, + "args": { + "External id": 1419164,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534642893.751, "dur": 2.378, + "args": { + "External id": 1419165,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643112.033, "dur": 3.740, + "args": { + "External id": 1419166,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 7069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534643121.406, "dur": 47.956, + "args": { + "External id": 1419167,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 7070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643136.619, "dur": 1.318, + "args": { + "External id": 1419168,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 7071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534643176.392, "dur": 37.740, + "args": { + "External id": 1419169,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 7072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534643180.752, "dur": 33.130, + "args": { + "External id": 1419170,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 7073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643185.693, "dur": 5.286, + "args": { + "External id": 1419171,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534643192.834, "dur": 20.464, + "args": { + "External id": 1419172,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 7075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534643219.446, "dur": 6.273, + "args": { + "External id": 1419173,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 7076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643221.052, "dur": 4.538, + "args": { + "External id": 1419174,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 7077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534643233.595, "dur": 4.583, + "args": { + "External id": 1419175,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643237.052, "dur": 0.965, + "args": { + "External id": 1419176,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534643258.745, "dur": 20.176, + "args": { + "External id": 1419177,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534643297.678, "dur": 11.194, + "args": { + "External id": 1419178,"Record function id": 0, "Ev Idx": 7081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534643300.975, "dur": 7.207, + "args": { + "External id": 1419179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534643303.677, "dur": 3.310, + "args": { + "External id": 1419180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534643304.894, "dur": 1.982, + "args": { + "External id": 1419181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534643313.617, "dur": 8.528, + "args": { + "External id": 1419182,"Record function id": 0, "Sequence number": 15109158, "Fwd thread id": 1, "Ev Idx": 7085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534643316.042, "dur": 1.500, + "args": { + "External id": 1419183,"Sequence number": 15109158, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7086 + } + }, + { + "ph": "f", "id": 361, "pid": 2338710, "tid": 2379450, "ts": 6410534643316.042, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534643326.966, "dur": 503.551, + "args": { + "External id": 1419184,"Record function id": 0, "Sequence number": 15109157, "Fwd thread id": 1, "Ev Idx": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534643328.659, "dur": 486.767, + "args": { + "External id": 1419185,"Sequence number": 15109157, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7088 + } + }, + { + "ph": "f", "id": 362, "pid": 2338710, "tid": 2379450, "ts": 6410534643328.659, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534643365.902, "dur": 10.357, + "args": { + "External id": 1419186,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534643372.157, "dur": 3.745, + "args": { + "External id": 1419187,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 7090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534643380.067, "dur": 6.105, + "args": { + "External id": 1419188,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534643382.038, "dur": 3.270, + "args": { + "External id": 1419189,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643384.052, "dur": 1.028, + "args": { + "External id": 1419190,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2379450, + "ts": 6410534643390.123, "dur": 125.245, + "args": { + "External id": 1419191,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 7094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534643393.477, "dur": 4.115, + "args": { + "External id": 1419192,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 7095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534643394.255, "dur": 2.742, + "args": { + "External id": 1419193,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 7096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643395.645, "dur": 1.224, + "args": { + "External id": 1419194,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 7097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2379450, + "ts": 6410534643399.032, "dur": 115.637, + "args": { + "External id": 1419195,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 7098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534643400.647, "dur": 112.872, + "args": { + "External id": 1419196,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 7099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534643522.139, "dur": 4.007, + "args": { + "External id": 1419197,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 7100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643523.930, "dur": 2.069, + "args": { + "External id": 1419198,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 7101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534643566.962, "dur": 5.201, + "args": { + "External id": 1419199,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534643573.850, "dur": 5.516, + "args": { + "External id": 1419200,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534643580.648, "dur": 3.138, + "args": { + "External id": 1419201,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534643621.149, "dur": 3.190, + "args": { + "External id": 1419202,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643622.319, "dur": 1.818, + "args": { + "External id": 1419203,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338710, "tid": 2379450, + "ts": 6410534643651.232, "dur": 139.832, + "args": { + "External id": 1419204,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 7107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410534643659.085, "dur": 6.567, + "args": { + "External id": 1419205,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643663.373, "dur": 1.106, + "args": { + "External id": 1419206,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 7109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534643667.759, "dur": 5.849, + "args": { + "External id": 1419207,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 7110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643672.034, "dur": 0.816, + "args": { + "External id": 1419208,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 7111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2379450, + "ts": 6410534643675.379, "dur": 3.393, + "args": { + "External id": 1419209,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 7112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643677.724, "dur": 0.589, + "args": { + "External id": 1419210,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 7113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534643679.576, "dur": 3.435, + "args": { + "External id": 1419211,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 7114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643681.605, "dur": 0.854, + "args": { + "External id": 1419212,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 7115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534643687.433, "dur": 5.505, + "args": { + "External id": 1419213,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 7116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643691.951, "dur": 0.555, + "args": { + "External id": 1419214,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 7117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534643694.208, "dur": 9.194, + "args": { + "External id": 1419215,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 7118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534643698.762, "dur": 4.427, + "args": { + "External id": 1419216,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 7119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534643704.673, "dur": 2.973, + "args": { + "External id": 1419217,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 7120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643706.776, "dur": 0.480, + "args": { + "External id": 1419218,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 7121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534643710.827, "dur": 2.587, + "args": { + "External id": 1419219,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 7122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643711.565, "dur": 1.742, + "args": { + "External id": 1419220,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 7123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410534643714.726, "dur": 63.304, + "args": { + "External id": 1419221,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 7124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643780.332, "dur": 1.392, + "args": { + "External id": 1419222,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 7125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338710, "tid": 2379450, + "ts": 6410534643782.939, "dur": 3.458, + "args": { + "External id": 1419223,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 7126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643785.213, "dur": 0.420, + "args": { + "External id": 1419224,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 7127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643788.865, "dur": 0.942, + "args": { + "External id": 1419225,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 7128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534643843.921, "dur": 10.578, + "args": { + "External id": 1419226,"Record function id": 0, "Ev Idx": 7129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534643846.098, "dur": 7.609, + "args": { + "External id": 1419227,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534643848.580, "dur": 4.016, + "args": { + "External id": 1419228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534643849.786, "dur": 2.673, + "args": { + "External id": 1419229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534643859.107, "dur": 9.339, + "args": { + "External id": 1419230,"Record function id": 0, "Sequence number": 15109156, "Fwd thread id": 1, "Ev Idx": 7133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534643860.399, "dur": 4.536, + "args": { + "External id": 1419231,"Sequence number": 15109156, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 7134 + } + }, + { + "ph": "f", "id": 363, "pid": 2338710, "tid": 2379450, "ts": 6410534643860.399, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534643862.375, "dur": 2.270, + "args": { + "External id": 1419232,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534643863.351, "dur": 1.111, + "args": { + "External id": 1419233,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534643872.960, "dur": 132.064, + "args": { + "External id": 1419234,"Record function id": 0, "Sequence number": 15109155, "Fwd thread id": 1, "Ev Idx": 7137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534643874.066, "dur": 122.898, + "args": { + "External id": 1419235,"Sequence number": 15109155, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 7138 + } + }, + { + "ph": "f", "id": 364, "pid": 2338710, "tid": 2379450, "ts": 6410534643874.066, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534643878.786, "dur": 9.382, + "args": { + "External id": 1419236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 7139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534643880.272, "dur": 7.125, + "args": { + "External id": 1419237,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 7140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643884.280, "dur": 2.906, + "args": { + "External id": 1419238,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 7141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534643889.262, "dur": 50.399, + "args": { + "External id": 1419239,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 7142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534643941.303, "dur": 4.330, + "args": { + "External id": 1419240,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534643942.067, "dur": 2.795, + "args": { + "External id": 1419241,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 7144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643943.740, "dur": 0.937, + "args": { + "External id": 1419242,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 7145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534643947.547, "dur": 6.857, + "args": { + "External id": 1419243,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534643948.948, "dur": 4.816, + "args": { + "External id": 1419244,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534643953.130, "dur": 0.520, + "args": { + "External id": 1419245,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534643955.124, "dur": 40.852, + "args": { + "External id": 1419246,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 7149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644010.829, "dur": 7.618, + "args": { + "External id": 1419247,"Record function id": 0, "Sequence number": 15109154, "Fwd thread id": 1, "Ev Idx": 7150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644011.936, "dur": 4.806, + "args": { + "External id": 1419248,"Sequence number": 15109154, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7151 + } + }, + { + "ph": "f", "id": 365, "pid": 2338710, "tid": 2379450, "ts": 6410534644011.936, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534644013.867, "dur": 2.700, + "args": { + "External id": 1419249,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644015.048, "dur": 1.394, + "args": { + "External id": 1419250,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644022.500, "dur": 11.520, + "args": { + "External id": 1419251,"Record function id": 0, "Sequence number": 15109153, "Fwd thread id": 1, "Ev Idx": 7154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644023.397, "dur": 7.590, + "args": { + "External id": 1419252,"Sequence number": 15109153, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7155 + } + }, + { + "ph": "f", "id": 366, "pid": 2338710, "tid": 2379450, "ts": 6410534644023.397, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534644024.597, "dur": 6.136, + "args": { + "External id": 1419253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534644025.407, "dur": 4.705, + "args": { + "External id": 1419254,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644029.314, "dur": 0.560, + "args": { + "External id": 1419255,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534644038.834, "dur": 8.366, + "args": { + "External id": 1419256,"Record function id": 0, "Ev Idx": 7159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534644040.180, "dur": 6.466, + "args": { + "External id": 1419257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534644041.373, "dur": 4.960, + "args": { + "External id": 1419258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534644042.112, "dur": 4.137, + "args": { + "External id": 1419259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644050.970, "dur": 49.582, + "args": { + "External id": 1419260,"Record function id": 0, "Sequence number": 15109152, "Fwd thread id": 1, "Ev Idx": 7163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644052.133, "dur": 45.157, + "args": { + "External id": 1419261,"Sequence number": 15109152, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 7164 + } + }, + { + "ph": "f", "id": 367, "pid": 2338710, "tid": 2379450, "ts": 6410534644052.133, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534644053.532, "dur": 43.453, + "args": { + "External id": 1419262,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644094.360, "dur": 2.183, + "args": { + "External id": 1419263,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644106.928, "dur": 148.379, + "args": { + "External id": 1419264,"Record function id": 0, "Sequence number": 15109151, "Fwd thread id": 1, "Ev Idx": 7167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644133.647, "dur": 111.724, + "args": { + "External id": 1419265,"Sequence number": 15109151, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 7168 + } + }, + { + "ph": "f", "id": 368, "pid": 2338710, "tid": 2379450, "ts": 6410534644133.647, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534644137.510, "dur": 3.907, + "args": { + "External id": 1419266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 7169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534644138.350, "dur": 2.491, + "args": { + "External id": 1419267,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 7170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644140.011, "dur": 0.702, + "args": { + "External id": 1419268,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 7171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534644142.268, "dur": 49.300, + "args": { + "External id": 1419269,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 7172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534644193.082, "dur": 8.289, + "args": { + "External id": 1419270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534644193.775, "dur": 6.860, + "args": { + "External id": 1419271,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 7174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644198.059, "dur": 2.363, + "args": { + "External id": 1419272,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 7175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534644202.644, "dur": 3.634, + "args": { + "External id": 1419273,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534644203.562, "dur": 2.035, + "args": { + "External id": 1419274,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644205.040, "dur": 0.462, + "args": { + "External id": 1419275,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534644206.777, "dur": 37.671, + "args": { + "External id": 1419276,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 7179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644260.774, "dur": 40.971, + "args": { + "External id": 1419277,"Record function id": 0, "Sequence number": 15109150, "Fwd thread id": 1, "Ev Idx": 7180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644261.917, "dur": 4.798, + "args": { + "External id": 1419278,"Sequence number": 15109150, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7181 + } + }, + { + "ph": "f", "id": 369, "pid": 2338710, "tid": 2379450, "ts": 6410534644261.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534644264.305, "dur": 2.243, + "args": { + "External id": 1419279,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644265.269, "dur": 1.144, + "args": { + "External id": 1419280,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534644270.317, "dur": 27.719, + "args": { + "External id": 1419281,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644306.042, "dur": 10.752, + "args": { + "External id": 1419282,"Record function id": 0, "Sequence number": 15109149, "Fwd thread id": 1, "Ev Idx": 7185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644309.147, "dur": 4.948, + "args": { + "External id": 1419283,"Sequence number": 15109149, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7186 + } + }, + { + "ph": "f", "id": 370, "pid": 2338710, "tid": 2379450, "ts": 6410534644309.147, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534644310.107, "dur": 3.742, + "args": { + "External id": 1419284,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534644310.933, "dur": 2.311, + "args": { + "External id": 1419285,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644312.504, "dur": 0.608, + "args": { + "External id": 1419286,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534644321.913, "dur": 6.167, + "args": { + "External id": 1419287,"Record function id": 0, "Ev Idx": 7190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534644323.313, "dur": 4.214, + "args": { + "External id": 1419288,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534644324.553, "dur": 2.581, + "args": { + "External id": 1419289,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534644325.295, "dur": 1.740, + "args": { + "External id": 1419290,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534644333.162, "dur": 517.990, + "args": { + "External id": 1419291,"Record function id": 0, "Sequence number": 15109148, "Fwd thread id": 1, "Ev Idx": 7194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534644338.465, "dur": 469.084, + "args": { + "External id": 1419292,"Sequence number": 15109148, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 7195 + } + }, + { + "ph": "f", "id": 371, "pid": 2338710, "tid": 2379450, "ts": 6410534644338.465, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2379450, + "ts": 6410534644365.466, "dur": 39.148, + "args": { + "External id": 1419293,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534644367.276, "dur": 37.120, + "args": { + "External id": 1419294,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534644370.469, "dur": 6.446, + "args": { + "External id": 1419295,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 7198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534644373.337, "dur": 2.962, + "args": { + "External id": 1419296,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534644378.593, "dur": 25.286, + "args": { + "External id": 1419297,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534644437.365, "dur": 3.709, + "args": { + "External id": 1419298,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644438.699, "dur": 2.098, + "args": { + "External id": 1419299,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534644446.120, "dur": 1.902, + "args": { + "External id": 1419300,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644446.794, "dur": 1.116, + "args": { + "External id": 1419301,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534644464.197, "dur": 3.711, + "args": { + "External id": 1419302,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534644481.414, "dur": 3.150, + "args": { + "External id": 1419303,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644678.940, "dur": 5.839, + "args": { + "External id": 1419304,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 7207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534644689.856, "dur": 39.716, + "args": { + "External id": 1419305,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 7208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644700.391, "dur": 1.138, + "args": { + "External id": 1419306,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 7209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534644736.391, "dur": 34.288, + "args": { + "External id": 1419307,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 7210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534644738.208, "dur": 32.223, + "args": { + "External id": 1419308,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 7211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644745.042, "dur": 5.217, + "args": { + "External id": 1419309,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534644751.882, "dur": 17.876, + "args": { + "External id": 1419310,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 7213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534644776.301, "dur": 3.381, + "args": { + "External id": 1419311,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 7214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644778.188, "dur": 1.316, + "args": { + "External id": 1419312,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 7215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534644786.914, "dur": 3.030, + "args": { + "External id": 1419313,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644788.223, "dur": 1.575, + "args": { + "External id": 1419314,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534644795.087, "dur": 2.430, + "args": { + "External id": 1419315,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644796.196, "dur": 1.196, + "args": { + "External id": 1419316,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534644828.745, "dur": 20.847, + "args": { + "External id": 1419317,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534644865.555, "dur": 9.594, + "args": { + "External id": 1419318,"Record function id": 0, "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534644867.976, "dur": 6.501, + "args": { + "External id": 1419319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534644870.518, "dur": 2.940, + "args": { + "External id": 1419320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534644871.490, "dur": 1.853, + "args": { + "External id": 1419321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644879.508, "dur": 9.214, + "args": { + "External id": 1419322,"Record function id": 0, "Sequence number": 15109147, "Fwd thread id": 1, "Ev Idx": 7225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644881.094, "dur": 4.785, + "args": { + "External id": 1419323,"Sequence number": 15109147, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7226 + } + }, + { + "ph": "f", "id": 372, "pid": 2338710, "tid": 2379450, "ts": 6410534644881.094, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534644883.066, "dur": 2.556, + "args": { + "External id": 1419324,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534644884.253, "dur": 1.219, + "args": { + "External id": 1419325,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644892.930, "dur": 204.411, + "args": { + "External id": 1419326,"Record function id": 0, "Sequence number": 15109146, "Fwd thread id": 1, "Ev Idx": 7229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534644894.028, "dur": 154.262, + "args": { + "External id": 1419327,"Sequence number": 15109146, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7230 + } + }, + { + "ph": "f", "id": 373, "pid": 2338710, "tid": 2379450, "ts": 6410534644894.028, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534644900.033, "dur": 5.021, + "args": { + "External id": 1419328,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534644901.616, "dur": 2.739, + "args": { + "External id": 1419329,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 7232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644903.293, "dur": 0.869, + "args": { + "External id": 1419330,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 7233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534644906.433, "dur": 77.921, + "args": { + "External id": 1419331,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 7234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534644985.802, "dur": 7.049, + "args": { + "External id": 1419332,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534644987.057, "dur": 4.871, + "args": { + "External id": 1419333,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644988.892, "dur": 2.811, + "args": { + "External id": 1419334,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534644996.963, "dur": 6.770, + "args": { + "External id": 1419335,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534644998.433, "dur": 4.600, + "args": { + "External id": 1419336,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534644999.870, "dur": 3.041, + "args": { + "External id": 1419337,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534645004.264, "dur": 42.933, + "args": { + "External id": 1419338,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 7241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534645107.282, "dur": 10.266, + "args": { + "External id": 1419339,"Record function id": 0, "Sequence number": 15109145, "Fwd thread id": 1, "Ev Idx": 7242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534645108.704, "dur": 6.318, + "args": { + "External id": 1419340,"Sequence number": 15109145, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7243 + } + }, + { + "ph": "f", "id": 374, "pid": 2338710, "tid": 2379450, "ts": 6410534645108.704, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534645111.353, "dur": 3.464, + "args": { + "External id": 1419341,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534645112.527, "dur": 2.175, + "args": { + "External id": 1419342,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534645121.852, "dur": 13.338, + "args": { + "External id": 1419343,"Record function id": 0, "Sequence number": 15109144, "Fwd thread id": 1, "Ev Idx": 7246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534645123.143, "dur": 8.954, + "args": { + "External id": 1419344,"Sequence number": 15109144, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7247 + } + }, + { + "ph": "f", "id": 375, "pid": 2338710, "tid": 2379450, "ts": 6410534645123.143, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534645124.452, "dur": 7.387, + "args": { + "External id": 1419345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534645128.041, "dur": 3.158, + "args": { + "External id": 1419346,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645130.148, "dur": 0.938, + "args": { + "External id": 1419347,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534645140.327, "dur": 8.246, + "args": { + "External id": 1419348,"Record function id": 0, "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534645142.589, "dur": 5.326, + "args": { + "External id": 1419349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534645144.502, "dur": 3.040, + "args": { + "External id": 1419350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534645145.757, "dur": 1.638, + "args": { + "External id": 1419351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534645152.357, "dur": 8.056, + "args": { + "External id": 1419352,"Record function id": 0, "Sequence number": 15109143, "Fwd thread id": 1, "Ev Idx": 7255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534645153.473, "dur": 4.411, + "args": { + "External id": 1419353,"Sequence number": 15109143, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7256 + } + }, + { + "ph": "f", "id": 376, "pid": 2338710, "tid": 2379450, "ts": 6410534645153.473, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534645155.221, "dur": 2.491, + "args": { + "External id": 1419354,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534645156.277, "dur": 1.315, + "args": { + "External id": 1419355,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534645165.841, "dur": 437.207, + "args": { + "External id": 1419356,"Record function id": 0, "Sequence number": 15109142, "Fwd thread id": 1, "Ev Idx": 7259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534645167.306, "dur": 410.611, + "args": { + "External id": 1419357,"Sequence number": 15109142, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 7260 + } + }, + { + "ph": "f", "id": 377, "pid": 2338710, "tid": 2379450, "ts": 6410534645167.306, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534645187.741, "dur": 8.880, + "args": { + "External id": 1419358,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 7261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645191.143, "dur": 4.928, + "args": { + "External id": 1419359,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534645199.118, "dur": 5.368, + "args": { + "External id": 1419360,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 7263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645201.162, "dur": 2.973, + "args": { + "External id": 1419361,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534645206.429, "dur": 5.340, + "args": { + "External id": 1419362,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 7265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645208.068, "dur": 3.485, + "args": { + "External id": 1419363,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534645240.818, "dur": 306.058, + "args": { + "External id": 1419364,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534645337.011, "dur": 4.825, + "args": { + "External id": 1419365,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534645344.274, "dur": 2.887, + "args": { + "External id": 1419366,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534645348.957, "dur": 1.856, + "args": { + "External id": 1419367,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534645352.089, "dur": 2.408, + "args": { + "External id": 1419368,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534645408.745, "dur": 23.375, + "args": { + "External id": 1419369,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534645412.582, "dur": 18.947, + "args": { + "External id": 1419370,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534645435.033, "dur": 34.070, + "args": { + "External id": 1419371,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645440.716, "dur": 1.438, + "args": { + "External id": 1419372,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534645470.816, "dur": 4.381, + "args": { + "External id": 1419373,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534645474.323, "dur": 0.759, + "args": { + "External id": 1419374,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534645477.033, "dur": 18.450, + "args": { + "External id": 1419375,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645479.863, "dur": 0.856, + "args": { + "External id": 1419376,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534645563.363, "dur": 4.253, + "args": { + "External id": 1419377,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 7280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534645570.809, "dur": 0.779, + "args": { + "External id": 1419378,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2379450, + "ts": 6410534645574.163, "dur": 0.775, + "args": { + "External id": 1419379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534645614.757, "dur": 271.465, + "args": { + "External id": 1419380,"Record function id": 0, "Sequence number": 15109141, "Fwd thread id": 1, "Ev Idx": 7283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534645616.556, "dur": 260.454, + "args": { + "External id": 1419381,"Sequence number": 15109141, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7284 + } + }, + { + "ph": "f", "id": 378, "pid": 2338710, "tid": 2379450, "ts": 6410534645616.556, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534645641.393, "dur": 55.703, + "args": { + "External id": 1419382,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645645.314, "dur": 7.049, + "args": { + "External id": 1419383,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534645654.383, "dur": 42.120, + "args": { + "External id": 1419384,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 7287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534645709.184, "dur": 5.898, + "args": { + "External id": 1419385,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 7288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645711.874, "dur": 2.774, + "args": { + "External id": 1419386,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534645894.824, "dur": 229.985, + "args": { + "External id": 1419387,"Record function id": 0, "Sequence number": 15109140, "Fwd thread id": 1, "Ev Idx": 7290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534645896.951, "dur": 218.471, + "args": { + "External id": 1419388,"Sequence number": 15109140, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 7291 + } + }, + { + "ph": "f", "id": 379, "pid": 2338710, "tid": 2379450, "ts": 6410534645896.951, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2379450, + "ts": 6410534645909.727, "dur": 46.247, + "args": { + "External id": 1419389,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645913.269, "dur": 3.008, + "args": { + "External id": 1419390,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534645917.604, "dur": 37.719, + "args": { + "External id": 1419391,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 7294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2379450, + "ts": 6410534645964.503, "dur": 5.687, + "args": { + "External id": 1419392,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 7295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534645966.984, "dur": 2.905, + "args": { + "External id": 1419393,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646135.511, "dur": 19.972, + "args": { + "External id": 1419394,"Record function id": 0, "Sequence number": 15109139, "Fwd thread id": 1, "Ev Idx": 7297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646139.998, "dur": 11.845, + "args": { + "External id": 1419395,"Sequence number": 15109139, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7298 + } + }, + { + "ph": "f", "id": 380, "pid": 2338710, "tid": 2379450, "ts": 6410534646139.998, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646143.438, "dur": 8.139, + "args": { + "External id": 1419396,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646145.468, "dur": 5.909, + "args": { + "External id": 1419397,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646159.433, "dur": 7.618, + "args": { + "External id": 1419398,"Record function id": 0, "Sequence number": 15109138, "Fwd thread id": 1, "Ev Idx": 7301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646160.287, "dur": 4.524, + "args": { + "External id": 1419399,"Sequence number": 15109138, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7302 + } + }, + { + "ph": "f", "id": 381, "pid": 2338710, "tid": 2379450, "ts": 6410534646160.287, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646162.141, "dur": 2.510, + "args": { + "External id": 1419400,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646163.343, "dur": 1.177, + "args": { + "External id": 1419401,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646171.075, "dur": 8.258, + "args": { + "External id": 1419402,"Record function id": 0, "Sequence number": 15109137, "Fwd thread id": 1, "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646171.842, "dur": 4.574, + "args": { + "External id": 1419403,"Sequence number": 15109137, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 7306 + } + }, + { + "ph": "f", "id": 382, "pid": 2338710, "tid": 2379450, "ts": 6410534646171.842, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646173.706, "dur": 2.522, + "args": { + "External id": 1419404,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646174.894, "dur": 1.214, + "args": { + "External id": 1419405,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646183.414, "dur": 9.733, + "args": { + "External id": 1419406,"Record function id": 0, "Sequence number": 15109136, "Fwd thread id": 1, "Ev Idx": 7309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646184.403, "dur": 6.220, + "args": { + "External id": 1419407,"Sequence number": 15109136, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 7310 + } + }, + { + "ph": "f", "id": 383, "pid": 2338710, "tid": 2379450, "ts": 6410534646184.403, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646185.990, "dur": 4.469, + "args": { + "External id": 1419408,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646189.211, "dur": 1.137, + "args": { + "External id": 1419409,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646197.137, "dur": 181.456, + "args": { + "External id": 1419410,"Record function id": 0, "Sequence number": 15109135, "Fwd thread id": 1, "Ev Idx": 7313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646198.087, "dur": 171.998, + "args": { + "External id": 1419411,"Sequence number": 15109135, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7314 + } + }, + { + "ph": "f", "id": 384, "pid": 2338710, "tid": 2379450, "ts": 6410534646198.087, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646202.670, "dur": 9.467, + "args": { + "External id": 1419412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646204.733, "dur": 6.658, + "args": { + "External id": 1419413,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 7316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646207.101, "dur": 3.994, + "args": { + "External id": 1419414,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 7317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534646216.113, "dur": 83.035, + "args": { + "External id": 1419415,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 7318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646300.849, "dur": 6.023, + "args": { + "External id": 1419416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646301.963, "dur": 4.086, + "args": { + "External id": 1419417,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 7320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646304.001, "dur": 1.893, + "args": { + "External id": 1419418,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 7321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646308.975, "dur": 7.009, + "args": { + "External id": 1419419,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646310.651, "dur": 4.691, + "args": { + "External id": 1419420,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646314.731, "dur": 0.532, + "args": { + "External id": 1419421,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534646316.780, "dur": 52.264, + "args": { + "External id": 1419422,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 7325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646384.246, "dur": 8.754, + "args": { + "External id": 1419423,"Record function id": 0, "Sequence number": 15109134, "Fwd thread id": 1, "Ev Idx": 7326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646385.684, "dur": 4.869, + "args": { + "External id": 1419424,"Sequence number": 15109134, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7327 + } + }, + { + "ph": "f", "id": 385, "pid": 2338710, "tid": 2379450, "ts": 6410534646385.684, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646387.867, "dur": 2.530, + "args": { + "External id": 1419425,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646388.940, "dur": 1.329, + "args": { + "External id": 1419426,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646397.569, "dur": 12.531, + "args": { + "External id": 1419427,"Record function id": 0, "Sequence number": 15109133, "Fwd thread id": 1, "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646398.531, "dur": 8.467, + "args": { + "External id": 1419428,"Sequence number": 15109133, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7331 + } + }, + { + "ph": "f", "id": 386, "pid": 2338710, "tid": 2379450, "ts": 6410534646398.531, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646399.813, "dur": 6.931, + "args": { + "External id": 1419429,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646403.582, "dur": 2.521, + "args": { + "External id": 1419430,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646405.342, "dur": 0.630, + "args": { + "External id": 1419431,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534646435.562, "dur": 15.771, + "args": { + "External id": 1419432,"Record function id": 0, "Ev Idx": 7335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534646438.698, "dur": 11.610, + "args": { + "External id": 1419433,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534646442.278, "dur": 7.498, + "args": { + "External id": 1419434,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534646443.643, "dur": 5.886, + "args": { + "External id": 1419435,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646456.686, "dur": 8.570, + "args": { + "External id": 1419436,"Record function id": 0, "Sequence number": 15109132, "Fwd thread id": 1, "Ev Idx": 7339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646458.238, "dur": 4.140, + "args": { + "External id": 1419437,"Sequence number": 15109132, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 7340 + } + }, + { + "ph": "f", "id": 387, "pid": 2338710, "tid": 2379450, "ts": 6410534646458.238, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646459.928, "dur": 2.245, + "args": { + "External id": 1419438,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646460.598, "dur": 1.413, + "args": { + "External id": 1419439,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646469.316, "dur": 116.122, + "args": { + "External id": 1419440,"Record function id": 0, "Sequence number": 15109131, "Fwd thread id": 1, "Ev Idx": 7343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646472.183, "dur": 104.921, + "args": { + "External id": 1419441,"Sequence number": 15109131, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7344 + } + }, + { + "ph": "f", "id": 388, "pid": 2338710, "tid": 2379450, "ts": 6410534646472.183, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646475.383, "dur": 3.474, + "args": { + "External id": 1419442,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646476.109, "dur": 2.214, + "args": { + "External id": 1419443,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 7346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646477.394, "dur": 0.800, + "args": { + "External id": 1419444,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 7347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534646479.860, "dur": 40.370, + "args": { + "External id": 1419445,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 7348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646521.691, "dur": 7.304, + "args": { + "External id": 1419446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646522.369, "dur": 5.974, + "args": { + "External id": 1419447,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 7350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646526.499, "dur": 1.706, + "args": { + "External id": 1419448,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 7351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646530.514, "dur": 4.137, + "args": { + "External id": 1419449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646531.931, "dur": 2.126, + "args": { + "External id": 1419450,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646533.388, "dur": 0.541, + "args": { + "External id": 1419451,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534646535.510, "dur": 40.870, + "args": { + "External id": 1419452,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 7355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646590.669, "dur": 57.999, + "args": { + "External id": 1419453,"Record function id": 0, "Sequence number": 15109130, "Fwd thread id": 1, "Ev Idx": 7356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646600.209, "dur": 13.290, + "args": { + "External id": 1419454,"Sequence number": 15109130, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7357 + } + }, + { + "ph": "f", "id": 389, "pid": 2338710, "tid": 2379450, "ts": 6410534646600.209, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646610.593, "dur": 2.745, + "args": { + "External id": 1419455,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646611.820, "dur": 1.372, + "args": { + "External id": 1419456,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2379450, + "ts": 6410534646617.435, "dur": 28.448, + "args": { + "External id": 1419457,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646653.308, "dur": 10.718, + "args": { + "External id": 1419458,"Record function id": 0, "Sequence number": 15109129, "Fwd thread id": 1, "Ev Idx": 7361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646654.690, "dur": 7.212, + "args": { + "External id": 1419459,"Sequence number": 15109129, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7362 + } + }, + { + "ph": "f", "id": 390, "pid": 2338710, "tid": 2379450, "ts": 6410534646654.690, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646657.576, "dur": 4.076, + "args": { + "External id": 1419460,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646658.732, "dur": 2.277, + "args": { + "External id": 1419461,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646660.331, "dur": 0.554, + "args": { + "External id": 1419462,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534646668.878, "dur": 5.862, + "args": { + "External id": 1419463,"Record function id": 0, "Ev Idx": 7366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534646670.489, "dur": 3.732, + "args": { + "External id": 1419464,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534646671.799, "dur": 2.085, + "args": { + "External id": 1419465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534646672.652, "dur": 1.126, + "args": { + "External id": 1419466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646678.760, "dur": 7.882, + "args": { + "External id": 1419467,"Record function id": 0, "Sequence number": 15109128, "Fwd thread id": 1, "Ev Idx": 7370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646679.979, "dur": 3.744, + "args": { + "External id": 1419468,"Sequence number": 15109128, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7371 + } + }, + { + "ph": "f", "id": 391, "pid": 2338710, "tid": 2379450, "ts": 6410534646679.979, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646681.715, "dur": 1.838, + "args": { + "External id": 1419469,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646682.461, "dur": 0.988, + "args": { + "External id": 1419470,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646690.452, "dur": 116.274, + "args": { + "External id": 1419471,"Record function id": 0, "Sequence number": 15109127, "Fwd thread id": 1, "Ev Idx": 7374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646693.742, "dur": 102.880, + "args": { + "External id": 1419472,"Sequence number": 15109127, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7375 + } + }, + { + "ph": "f", "id": 392, "pid": 2338710, "tid": 2379450, "ts": 6410534646693.742, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646697.174, "dur": 2.803, + "args": { + "External id": 1419473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646697.903, "dur": 1.570, + "args": { + "External id": 1419474,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 7377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646699.003, "dur": 0.351, + "args": { + "External id": 1419475,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 7378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534646701.020, "dur": 40.153, + "args": { + "External id": 1419476,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 7379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646742.795, "dur": 6.759, + "args": { + "External id": 1419477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646743.573, "dur": 5.148, + "args": { + "External id": 1419478,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646747.866, "dur": 0.719, + "args": { + "External id": 1419479,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646750.889, "dur": 4.425, + "args": { + "External id": 1419480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646752.340, "dur": 2.264, + "args": { + "External id": 1419481,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646753.958, "dur": 0.571, + "args": { + "External id": 1419482,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534646756.316, "dur": 39.559, + "args": { + "External id": 1419483,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 7386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646811.945, "dur": 35.218, + "args": { + "External id": 1419484,"Record function id": 0, "Sequence number": 15109126, "Fwd thread id": 1, "Ev Idx": 7387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646813.379, "dur": 8.952, + "args": { + "External id": 1419485,"Sequence number": 15109126, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7388 + } + }, + { + "ph": "f", "id": 393, "pid": 2338710, "tid": 2379450, "ts": 6410534646813.379, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646817.908, "dur": 4.243, + "args": { + "External id": 1419486,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646819.341, "dur": 2.638, + "args": { + "External id": 1419487,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534646825.569, "dur": 17.865, + "args": { + "External id": 1419488,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646851.781, "dur": 8.846, + "args": { + "External id": 1419489,"Record function id": 0, "Sequence number": 15109125, "Fwd thread id": 1, "Ev Idx": 7392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338710, "tid": 2379450, + "ts": 6410534646853.026, "dur": 5.771, + "args": { + "External id": 1419490,"Sequence number": 15109125, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7393 + } + }, + { + "ph": "f", "id": 394, "pid": 2338710, "tid": 2379450, "ts": 6410534646853.026, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2379450, + "ts": 6410534646854.268, "dur": 4.281, + "args": { + "External id": 1419491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2379450, + "ts": 6410534646855.211, "dur": 2.734, + "args": { + "External id": 1419492,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534646857.271, "dur": 0.554, + "args": { + "External id": 1419493,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534646865.145, "dur": 5.737, + "args": { + "External id": 1419494,"Record function id": 0, "Ev Idx": 7397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534646866.426, "dur": 3.961, + "args": { + "External id": 1419495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534646867.524, "dur": 2.137, + "args": { + "External id": 1419496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534646868.412, "dur": 1.140, + "args": { + "External id": 1419497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534646875.743, "dur": 475.397, + "args": { + "External id": 1419498,"Record function id": 0, "Sequence number": 15109124, "Fwd thread id": 1, "Ev Idx": 7401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534646877.272, "dur": 429.708, + "args": { + "External id": 1419499,"Sequence number": 15109124, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7402 + } + }, + { + "ph": "f", "id": 395, "pid": 2338710, "tid": 2379450, "ts": 6410534646877.272, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534646920.072, "dur": 2.209, + "args": { + "External id": 1419500,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534646920.760, "dur": 1.369, + "args": { + "External id": 1419501,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534646938.692, "dur": 5.080, + "args": { + "External id": 1419502,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534646954.475, "dur": 2.718, + "args": { + "External id": 1419503,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534647172.236, "dur": 3.712, + "args": { + "External id": 1419504,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 7407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534647185.657, "dur": 46.597, + "args": { + "External id": 1419505,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 7408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647201.685, "dur": 1.175, + "args": { + "External id": 1419506,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 7409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534647239.271, "dur": 38.187, + "args": { + "External id": 1419507,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 7410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534647243.913, "dur": 33.332, + "args": { + "External id": 1419508,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 7411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647249.788, "dur": 5.288, + "args": { + "External id": 1419509,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534647256.975, "dur": 19.748, + "args": { + "External id": 1419510,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 7413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2379450, + "ts": 6410534647282.873, "dur": 3.202, + "args": { + "External id": 1419511,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 7414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534647284.538, "dur": 1.394, + "args": { + "External id": 1419512,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 7415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534647294.104, "dur": 4.732, + "args": { + "External id": 1419513,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534647297.693, "dur": 1.035, + "args": { + "External id": 1419514,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534647324.185, "dur": 19.761, + "args": { + "External id": 1419515,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534647366.036, "dur": 10.447, + "args": { + "External id": 1419516,"Record function id": 0, "Ev Idx": 7419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534647368.973, "dur": 6.648, + "args": { + "External id": 1419517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534647371.253, "dur": 3.284, + "args": { + "External id": 1419518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534647372.493, "dur": 1.933, + "args": { + "External id": 1419519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534647381.290, "dur": 3249.019, + "args": { + "External id": 1419520,"Record function id": 0, "Ev Idx": 7423 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 2338710, "tid": 2379450, + "ts": 6410534647435.173, "dur": 1105.934, + "args": { + "External id": 1419521,"Record function id": 0, "Ev Idx": 7424 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.24", "pid": 2338710, "tid": 2379450, + "ts": 6410534647466.078, "dur": 1064.431, + "args": { + "External id": 1419522,"Record function id": 0, "Ev Idx": 7425 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410534647485.130, "dur": 1027.572, + "args": { + "External id": 1419523,"Record function id": 0, "Ev Idx": 7426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534647589.717, "dur": 8.697, + "args": { + "External id": 1419524,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410534647618.515, "dur": 37.191, + "args": { + "External id": 1419525,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647624.877, "dur": 1.460, + "args": { + "External id": 1419526,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647628.867, "dur": 0.662, + "args": { + "External id": 1419527,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647630.653, "dur": 0.565, + "args": { + "External id": 1419528,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647635.126, "dur": 0.348, + "args": { + "External id": 1419529,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647636.483, "dur": 3.101, + "args": { + "External id": 1419530,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647641.141, "dur": 1.116, + "args": { + "External id": 1419531,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647643.738, "dur": 0.453, + "args": { + "External id": 1419532,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647645.978, "dur": 0.609, + "args": { + "External id": 1419533,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647650.621, "dur": 0.377, + "args": { + "External id": 1419534,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534647669.515, "dur": 57.039, + "args": { + "External id": 1419535,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410534647772.131, "dur": 145.117, + "args": { + "External id": 1419536,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 7439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534647786.855, "dur": 4.914, + "args": { + "External id": 1419537,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410534647799.962, "dur": 11.007, + "args": { + "External id": 1419538,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534647804.511, "dur": 6.019, + "args": { + "External id": 1419539,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 7442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647808.137, "dur": 0.742, + "args": { + "External id": 1419540,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410534647818.618, "dur": 33.040, + "args": { + "External id": 1419541,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647820.745, "dur": 0.584, + "args": { + "External id": 1419542,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647823.777, "dur": 2.898, + "args": { + "External id": 1419543,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647828.816, "dur": 0.603, + "args": { + "External id": 1419544,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647831.124, "dur": 0.614, + "args": { + "External id": 1419545,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647833.104, "dur": 0.595, + "args": { + "External id": 1419546,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647837.556, "dur": 0.435, + "args": { + "External id": 1419547,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647839.028, "dur": 0.538, + "args": { + "External id": 1419548,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647841.534, "dur": 1.743, + "args": { + "External id": 1419549,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534647844.478, "dur": 0.336, + "args": { + "External id": 1419550,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534647866.235, "dur": 39.382, + "args": { + "External id": 1419551,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410534647985.291, "dur": 382.683, + "args": { + "External id": 1419552,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 7455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410534648019.980, "dur": 341.698, + "args": { + "External id": 1419553,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7456, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410534648031.468, "dur": 323.128, + "args": { + "External id": 1419554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 7457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410534648396.837, "dur": 2.657, + "args": { + "External id": 1419555,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7458, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534648551.629, "dur": 2052.142, + "args": { + "External id": 1419556,"Sequence number": 15109123, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7459 + } + }, + { + "ph": "f", "id": 396, "pid": 2338710, "tid": 2379450, "ts": 6410534648551.629, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534648698.204, "dur": 131.557, + "args": { + "External id": 1419557,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 7460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410534648880.712, "dur": 47.695, + "args": { + "External id": 1419558,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 7461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410534648952.624, "dur": 57.402, + "args": { + "External id": 1419559,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 7462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534649021.015, "dur": 78.988, + "args": { + "External id": 1419560,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534649112.423, "dur": 49.460, + "args": { + "External id": 1419561,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534649170.510, "dur": 31.056, + "args": { + "External id": 1419562,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534649213.330, "dur": 31.013, + "args": { + "External id": 1419563,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410534649278.827, "dur": 28.064, + "args": { + "External id": 1419564,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 7467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410534649329.113, "dur": 32.083, + "args": { + "External id": 1419565,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410534649388.506, "dur": 23.960, + "args": { + "External id": 1419566,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410534649449.965, "dur": 21.334, + "args": { + "External id": 1419567,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534649485.356, "dur": 47.529, + "args": { + "External id": 1419568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534649537.768, "dur": 35.731, + "args": { + "External id": 1419569,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534649608.032, "dur": 283.342, + "args": { + "External id": 1419570,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534649705.076, "dur": 7.968, + "args": { + "External id": 1419571,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534649715.444, "dur": 2.639, + "args": { + "External id": 1419572,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534649719.649, "dur": 4.497, + "args": { + "External id": 1419573,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534649725.827, "dur": 4.824, + "args": { + "External id": 1419574,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534649776.504, "dur": 7.713, + "args": { + "External id": 1419575,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534649780.735, "dur": 3.279, + "args": { + "External id": 1419576,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534649786.211, "dur": 34.675, + "args": { + "External id": 1419577,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534649792.471, "dur": 2.120, + "args": { + "External id": 1419578,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534649822.625, "dur": 1.851, + "args": { + "External id": 1419579,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534649823.774, "dur": 0.570, + "args": { + "External id": 1419580,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534649825.691, "dur": 16.291, + "args": { + "External id": 1419581,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534649828.113, "dur": 0.844, + "args": { + "External id": 1419582,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410534649935.306, "dur": 30.436, + "args": { + "External id": 1419583,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410534649987.469, "dur": 16.996, + "args": { + "External id": 1419584,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534650012.920, "dur": 86.335, + "args": { + "External id": 1419585,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534650110.900, "dur": 50.370, + "args": { + "External id": 1419586,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534650174.587, "dur": 24.161, + "args": { + "External id": 1419587,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534650205.655, "dur": 33.806, + "args": { + "External id": 1419588,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534650247.397, "dur": 29.536, + "args": { + "External id": 1419589,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534650286.484, "dur": 32.915, + "args": { + "External id": 1419590,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410534650346.496, "dur": 28.394, + "args": { + "External id": 1419591,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 7494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410534650398.117, "dur": 46.062, + "args": { + "External id": 1419592,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410534650467.525, "dur": 20.572, + "args": { + "External id": 1419593,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410534650512.911, "dur": 16.629, + "args": { + "External id": 1419594,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410534650547.743, "dur": 17.278, + "args": { + "External id": 1419595,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 7498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650656.415, "dur": 17.387, + "args": { + "External id": 1419596,"Record function id": 0, "Ev Idx": 7499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650660.084, "dur": 12.527, + "args": { + "External id": 1419597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650665.205, "dur": 6.339, + "args": { + "External id": 1419598,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650666.922, "dur": 4.526, + "args": { + "External id": 1419599,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650678.169, "dur": 5.464, + "args": { + "External id": 1419600,"Record function id": 0, "Ev Idx": 7503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650679.879, "dur": 3.206, + "args": { + "External id": 1419601,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650680.838, "dur": 1.702, + "args": { + "External id": 1419602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650681.434, "dur": 0.962, + "args": { + "External id": 1419603,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650687.654, "dur": 7.358, + "args": { + "External id": 1419604,"Record function id": 0, "Ev Idx": 7507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650689.221, "dur": 5.233, + "args": { + "External id": 1419605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650689.954, "dur": 3.966, + "args": { + "External id": 1419606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650690.681, "dur": 3.095, + "args": { + "External id": 1419607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650698.898, "dur": 5.381, + "args": { + "External id": 1419608,"Record function id": 0, "Ev Idx": 7511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650700.263, "dur": 3.526, + "args": { + "External id": 1419609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650701.229, "dur": 1.950, + "args": { + "External id": 1419610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650701.843, "dur": 1.229, + "args": { + "External id": 1419611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650708.011, "dur": 5.422, + "args": { + "External id": 1419612,"Record function id": 0, "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650709.786, "dur": 3.053, + "args": { + "External id": 1419613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650710.708, "dur": 1.504, + "args": { + "External id": 1419614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650711.278, "dur": 0.860, + "args": { + "External id": 1419615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650717.136, "dur": 4.350, + "args": { + "External id": 1419616,"Record function id": 0, "Ev Idx": 7519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650718.488, "dur": 2.512, + "args": { + "External id": 1419617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650719.084, "dur": 1.294, + "args": { + "External id": 1419618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650719.601, "dur": 0.665, + "args": { + "External id": 1419619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650725.486, "dur": 4.673, + "args": { + "External id": 1419620,"Record function id": 0, "Ev Idx": 7523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650726.866, "dur": 2.831, + "args": { + "External id": 1419621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650727.446, "dur": 1.774, + "args": { + "External id": 1419622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650728.128, "dur": 1.012, + "args": { + "External id": 1419623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650733.875, "dur": 7.018, + "args": { + "External id": 1419624,"Record function id": 0, "Ev Idx": 7527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650735.389, "dur": 4.974, + "args": { + "External id": 1419625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650736.093, "dur": 3.653, + "args": { + "External id": 1419626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650738.870, "dur": 0.756, + "args": { + "External id": 1419627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650744.569, "dur": 4.118, + "args": { + "External id": 1419628,"Record function id": 0, "Ev Idx": 7531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534650745.766, "dur": 2.433, + "args": { + "External id": 1419629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650746.333, "dur": 1.379, + "args": { + "External id": 1419630,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534650746.875, "dur": 0.737, + "args": { + "External id": 1419631,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534650753.365, "dur": 280127.845, + "args": { + "External id": 1419632,"Record function id": 0, "Sequence number": 15109122, "Fwd thread id": 1, "Ev Idx": 7535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534650754.874, "dur": 280116.182, + "args": { + "External id": 1419633,"Sequence number": 15109122, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7536 + } + }, + { + "ph": "f", "id": 397, "pid": 2338710, "tid": 2379450, "ts": 6410534650754.874, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 2338710, "tid": 2379450, + "ts": 6410534650793.970, "dur": 51.784, + "args": { + "External id": 1419634,"Record function id": 0, "Ev Idx": 7537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 2338710, "tid": 2379450, + "ts": 6410534650856.480, "dur": 101.187, + "args": { + "External id": 1419635,"Record function id": 0, "Ev Idx": 7538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 2338710, "tid": 2379450, + "ts": 6410534650964.544, "dur": 279896.872, + "args": { + "External id": 1419636,"Record function id": 0, "Ev Idx": 7539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534651032.609, "dur": 9.156, + "args": { + "External id": 1419637,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534651095.605, "dur": 8.569, + "args": { + "External id": 1419638,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410534651123.629, "dur": 278673.829, + "args": { + "External id": 1419639,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410534651142.859, "dur": 278639.382, + "args": { + "External id": 1419640,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534651267.034, "dur": 6.193, + "args": { + "External id": 1419641,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534651296.240, "dur": 278428.290, + "args": { + "External id": 1419642,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 7545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534651299.678, "dur": 278423.360, + "args": { + "External id": 1419643,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 7546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534651304.802, "dur": 13.557, + "args": { + "External id": 1419644,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534651321.113, "dur": 278394.952, + "args": { + "External id": 1419645,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 7548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534929931.006, "dur": 17.510, + "args": { + "External id": 1419646,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 7549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534929935.550, "dur": 12.422, + "args": { + "External id": 1419647,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410534929995.639, "dur": 387.640, + "args": { + "External id": 1419648,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 7551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410534930032.799, "dur": 344.155, + "args": { + "External id": 1419649,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7552, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410534930047.775, "dur": 323.417, + "args": { + "External id": 1419650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 7553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410534930412.032, "dur": 18.980, + "args": { + "External id": 1419651,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7554, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930505.503, "dur": 8.261, + "args": { + "External id": 1419652,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930531.530, "dur": 47.837, + "args": { + "External id": 1419653,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930592.678, "dur": 1.710, + "args": { + "External id": 1419654,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930600.766, "dur": 16.431, + "args": { + "External id": 1419655,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930624.673, "dur": 1.209, + "args": { + "External id": 1419656,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930631.093, "dur": 13.179, + "args": { + "External id": 1419657,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930649.849, "dur": 1.211, + "args": { + "External id": 1419658,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930656.118, "dur": 12.335, + "args": { + "External id": 1419659,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930674.215, "dur": 3.696, + "args": { + "External id": 1419660,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930682.694, "dur": 10.833, + "args": { + "External id": 1419661,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930698.611, "dur": 1.802, + "args": { + "External id": 1419662,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930707.703, "dur": 11.874, + "args": { + "External id": 1419663,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930725.305, "dur": 1.145, + "args": { + "External id": 1419664,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930731.497, "dur": 11.123, + "args": { + "External id": 1419665,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930747.773, "dur": 0.844, + "args": { + "External id": 1419666,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930754.783, "dur": 11.634, + "args": { + "External id": 1419667,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534930773.897, "dur": 1.218, + "args": { + "External id": 1419668,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410534930780.187, "dur": 11.536, + "args": { + "External id": 1419669,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 7572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534930899.421, "dur": 3476.406, + "args": { + "External id": 1419670,"Record function id": 0, "Ev Idx": 7573 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410534930923.839, "dur": 1314.749, + "args": { + "External id": 1419671,"Record function id": 0, "Ev Idx": 7574 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410534930942.282, "dur": 438.239, + "args": { + "External id": 1419672,"Record function id": 0, "Ev Idx": 7575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931042.807, "dur": 4.467, + "args": { + "External id": 1419673,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931089.474, "dur": 2.194, + "args": { + "External id": 1419674,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931096.634, "dur": 1.183, + "args": { + "External id": 1419675,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931100.037, "dur": 3.223, + "args": { + "External id": 1419676,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931105.251, "dur": 1.009, + "args": { + "External id": 1419677,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931108.376, "dur": 0.984, + "args": { + "External id": 1419678,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931113.565, "dur": 1.336, + "args": { + "External id": 1419679,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931123.386, "dur": 1.238, + "args": { + "External id": 1419680,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931126.560, "dur": 1.159, + "args": { + "External id": 1419681,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534931129.468, "dur": 0.839, + "args": { + "External id": 1419682,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534931157.540, "dur": 183.955, + "args": { + "External id": 1419683,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534931177.519, "dur": 157.645, + "args": { + "External id": 1419684,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534931196.475, "dur": 17.199, + "args": { + "External id": 1419685,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534931220.006, "dur": 82.311, + "args": { + "External id": 1419686,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 7589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534931223.067, "dur": 78.769, + "args": { + "External id": 1419687,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 7590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931227.541, "dur": 9.165, + "args": { + "External id": 1419688,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534931238.721, "dur": 62.340, + "args": { + "External id": 1419689,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 7592 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.23", "pid": 2338710, "tid": 2379450, + "ts": 6410534931511.257, "dur": 718.281, + "args": { + "External id": 1419690,"Record function id": 0, "Ev Idx": 7593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410534931533.474, "dur": 680.134, + "args": { + "External id": 1419691,"Record function id": 0, "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534931606.174, "dur": 6.788, + "args": { + "External id": 1419692,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410534931630.801, "dur": 34.752, + "args": { + "External id": 1419693,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931635.621, "dur": 2.053, + "args": { + "External id": 1419694,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931640.102, "dur": 1.978, + "args": { + "External id": 1419695,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931643.965, "dur": 0.508, + "args": { + "External id": 1419696,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931646.006, "dur": 0.465, + "args": { + "External id": 1419697,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931649.190, "dur": 0.456, + "args": { + "External id": 1419698,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931651.198, "dur": 0.315, + "args": { + "External id": 1419699,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931652.894, "dur": 3.158, + "args": { + "External id": 1419700,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931659.243, "dur": 0.445, + "args": { + "External id": 1419701,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931660.876, "dur": 0.455, + "args": { + "External id": 1419702,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534931678.362, "dur": 48.782, + "args": { + "External id": 1419703,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410534931764.260, "dur": 125.969, + "args": { + "External id": 1419704,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 7607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534931776.252, "dur": 3.844, + "args": { + "External id": 1419705,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410534931786.447, "dur": 12.076, + "args": { + "External id": 1419706,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410534931791.536, "dur": 6.450, + "args": { + "External id": 1419707,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 7610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931795.439, "dur": 0.903, + "args": { + "External id": 1419708,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410534931807.146, "dur": 27.895, + "args": { + "External id": 1419709,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931809.476, "dur": 0.445, + "args": { + "External id": 1419710,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931812.556, "dur": 0.370, + "args": { + "External id": 1419711,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931814.491, "dur": 0.345, + "args": { + "External id": 1419712,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931816.304, "dur": 3.798, + "args": { + "External id": 1419713,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931821.553, "dur": 0.302, + "args": { + "External id": 1419714,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931823.467, "dur": 0.415, + "args": { + "External id": 1419715,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931826.745, "dur": 0.291, + "args": { + "External id": 1419716,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931828.275, "dur": 0.502, + "args": { + "External id": 1419717,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534931830.307, "dur": 0.432, + "args": { + "External id": 1419718,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534931849.082, "dur": 32.614, + "args": { + "External id": 1419719,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410534931942.186, "dur": 180.326, + "args": { + "External id": 1419720,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 7623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410534931975.077, "dur": 142.505, + "args": { + "External id": 1419721,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7624, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410534931985.856, "dur": 126.074, + "args": { + "External id": 1419722,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 7625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410534932145.589, "dur": 2.661, + "args": { + "External id": 1419723,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7626, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534932246.716, "dur": 2102.067, + "args": { + "External id": 1419724,"Sequence number": 15109121, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7627 + } + }, + { + "ph": "f", "id": 398, "pid": 2338710, "tid": 2379450, "ts": 6410534932246.716, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534932379.701, "dur": 144.470, + "args": { + "External id": 1419725,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 7628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410534932580.257, "dur": 50.107, + "args": { + "External id": 1419726,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 7629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410534932652.087, "dur": 60.402, + "args": { + "External id": 1419727,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 7630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534932724.417, "dur": 36.096, + "args": { + "External id": 1419728,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534932770.350, "dur": 37.526, + "args": { + "External id": 1419729,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534932815.539, "dur": 32.884, + "args": { + "External id": 1419730,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534932856.544, "dur": 32.711, + "args": { + "External id": 1419731,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410534932919.216, "dur": 29.090, + "args": { + "External id": 1419732,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 7635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410534932974.417, "dur": 33.070, + "args": { + "External id": 1419733,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410534933033.565, "dur": 59.652, + "args": { + "External id": 1419734,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410534933119.652, "dur": 21.520, + "args": { + "External id": 1419735,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534933151.623, "dur": 49.391, + "args": { + "External id": 1419736,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534933205.232, "dur": 36.882, + "args": { + "External id": 1419737,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410534933278.345, "dur": 349.195, + "args": { + "External id": 1419738,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534933374.816, "dur": 7.165, + "args": { + "External id": 1419739,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534933384.576, "dur": 3.550, + "args": { + "External id": 1419740,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534933389.419, "dur": 2.529, + "args": { + "External id": 1419741,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534933393.861, "dur": 2.068, + "args": { + "External id": 1419742,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534933479.361, "dur": 7.354, + "args": { + "External id": 1419743,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534933481.832, "dur": 3.851, + "args": { + "External id": 1419744,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534933489.141, "dur": 39.732, + "args": { + "External id": 1419745,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534933496.648, "dur": 3.723, + "args": { + "External id": 1419746,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410534933531.163, "dur": 2.317, + "args": { + "External id": 1419747,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534933532.516, "dur": 0.820, + "args": { + "External id": 1419748,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410534933535.284, "dur": 19.304, + "args": { + "External id": 1419749,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534933537.761, "dur": 3.423, + "args": { + "External id": 1419750,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410534933676.758, "dur": 34.625, + "args": { + "External id": 1419751,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410534933734.300, "dur": 18.609, + "args": { + "External id": 1419752,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534933761.797, "dur": 55.175, + "args": { + "External id": 1419753,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534933824.958, "dur": 44.948, + "args": { + "External id": 1419754,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534933882.322, "dur": 25.837, + "args": { + "External id": 1419755,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534933914.249, "dur": 36.553, + "args": { + "External id": 1419756,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534933959.258, "dur": 31.752, + "args": { + "External id": 1419757,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410534933998.802, "dur": 34.054, + "args": { + "External id": 1419758,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410534934095.169, "dur": 37.824, + "args": { + "External id": 1419759,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 7662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410534934160.034, "dur": 31.573, + "args": { + "External id": 1419760,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410534934210.853, "dur": 21.669, + "args": { + "External id": 1419761,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410534934255.162, "dur": 17.374, + "args": { + "External id": 1419762,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410534934294.937, "dur": 19.407, + "args": { + "External id": 1419763,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 7666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934401.232, "dur": 34.364, + "args": { + "External id": 1419764,"Record function id": 0, "Ev Idx": 7667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934404.923, "dur": 28.899, + "args": { + "External id": 1419765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934409.903, "dur": 22.248, + "args": { + "External id": 1419766,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934411.767, "dur": 19.826, + "args": { + "External id": 1419767,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934443.507, "dur": 6.860, + "args": { + "External id": 1419768,"Record function id": 0, "Ev Idx": 7671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934445.495, "dur": 4.354, + "args": { + "External id": 1419769,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934447.147, "dur": 2.062, + "args": { + "External id": 1419770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934447.941, "dur": 1.121, + "args": { + "External id": 1419771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934454.447, "dur": 7.988, + "args": { + "External id": 1419772,"Record function id": 0, "Ev Idx": 7675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934455.894, "dur": 5.866, + "args": { + "External id": 1419773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934456.737, "dur": 4.554, + "args": { + "External id": 1419774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934457.828, "dur": 3.330, + "args": { + "External id": 1419775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934466.156, "dur": 42.391, + "args": { + "External id": 1419776,"Record function id": 0, "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934504.974, "dur": 3.031, + "args": { + "External id": 1419777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934505.914, "dur": 1.619, + "args": { + "External id": 1419778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934506.416, "dur": 1.005, + "args": { + "External id": 1419779,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934512.401, "dur": 4.480, + "args": { + "External id": 1419780,"Record function id": 0, "Ev Idx": 7683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934514.031, "dur": 2.375, + "args": { + "External id": 1419781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934514.630, "dur": 1.212, + "args": { + "External id": 1419782,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934515.006, "dur": 0.706, + "args": { + "External id": 1419783,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934520.506, "dur": 7.595, + "args": { + "External id": 1419784,"Record function id": 0, "Ev Idx": 7687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934521.956, "dur": 5.612, + "args": { + "External id": 1419785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934522.902, "dur": 4.234, + "args": { + "External id": 1419786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934526.067, "dur": 0.944, + "args": { + "External id": 1419787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934532.385, "dur": 4.753, + "args": { + "External id": 1419788,"Record function id": 0, "Ev Idx": 7691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934533.734, "dur": 2.914, + "args": { + "External id": 1419789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934534.852, "dur": 1.173, + "args": { + "External id": 1419790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934535.202, "dur": 0.720, + "args": { + "External id": 1419791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934541.032, "dur": 4.208, + "args": { + "External id": 1419792,"Record function id": 0, "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934542.541, "dur": 2.221, + "args": { + "External id": 1419793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934543.098, "dur": 1.203, + "args": { + "External id": 1419794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934543.414, "dur": 0.796, + "args": { + "External id": 1419795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934549.340, "dur": 4.497, + "args": { + "External id": 1419796,"Record function id": 0, "Ev Idx": 7699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410534934550.492, "dur": 2.731, + "args": { + "External id": 1419797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934551.124, "dur": 1.526, + "args": { + "External id": 1419798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410534934551.765, "dur": 0.796, + "args": { + "External id": 1419799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534934558.961, "dur": 78874.101, + "args": { + "External id": 1419800,"Record function id": 0, "Sequence number": 15109120, "Fwd thread id": 1, "Ev Idx": 7703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410534934560.617, "dur": 78846.879, + "args": { + "External id": 1419801,"Sequence number": 15109120, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7704 + } + }, + { + "ph": "f", "id": 399, "pid": 2338710, "tid": 2379450, "ts": 6410534934560.617, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410534934597.647, "dur": 47.894, + "args": { + "External id": 1419802,"Record function id": 0, "Ev Idx": 7705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410534934655.559, "dur": 77.324, + "args": { + "External id": 1419803,"Record function id": 0, "Ev Idx": 7706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 2338710, "tid": 2379450, + "ts": 6410534934740.021, "dur": 78658.621, + "args": { + "External id": 1419804,"Record function id": 0, "Ev Idx": 7707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534934849.070, "dur": 8.766, + "args": { + "External id": 1419805,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410534934868.982, "dur": 7.073, + "args": { + "External id": 1419806,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410534934894.400, "dur": 77394.800, + "args": { + "External id": 1419807,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410534934910.887, "dur": 77363.773, + "args": { + "External id": 1419808,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410534935022.970, "dur": 20.734, + "args": { + "External id": 1419809,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410534935130.616, "dur": 77096.972, + "args": { + "External id": 1419810,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 7713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410534935134.695, "dur": 77091.869, + "args": { + "External id": 1419811,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 7714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410534935142.369, "dur": 19.959, + "args": { + "External id": 1419812,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410534935165.753, "dur": 77057.645, + "args": { + "External id": 1419813,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 7716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535012411.255, "dur": 27.811, + "args": { + "External id": 1419814,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 7717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535012428.308, "dur": 10.041, + "args": { + "External id": 1419815,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535012475.918, "dur": 422.938, + "args": { + "External id": 1419816,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 7719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535012513.506, "dur": 379.457, + "args": { + "External id": 1419817,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7720, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535012531.193, "dur": 354.357, + "args": { + "External id": 1419818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 7721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535012924.796, "dur": 2.825, + "args": { + "External id": 1419819,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7722, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535012994.981, "dur": 7.699, + "args": { + "External id": 1419820,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013018.320, "dur": 79.836, + "args": { + "External id": 1419821,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013115.026, "dur": 3.135, + "args": { + "External id": 1419822,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013124.881, "dur": 17.166, + "args": { + "External id": 1419823,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013149.578, "dur": 1.378, + "args": { + "External id": 1419824,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013158.436, "dur": 12.452, + "args": { + "External id": 1419825,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013176.835, "dur": 1.063, + "args": { + "External id": 1419826,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013182.708, "dur": 12.571, + "args": { + "External id": 1419827,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013200.824, "dur": 3.723, + "args": { + "External id": 1419828,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013209.000, "dur": 12.199, + "args": { + "External id": 1419829,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013226.839, "dur": 1.744, + "args": { + "External id": 1419830,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013233.678, "dur": 12.178, + "args": { + "External id": 1419831,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013253.471, "dur": 1.075, + "args": { + "External id": 1419832,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013265.549, "dur": 12.012, + "args": { + "External id": 1419833,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013285.300, "dur": 0.950, + "args": { + "External id": 1419834,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013290.496, "dur": 12.606, + "args": { + "External id": 1419835,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013308.357, "dur": 1.092, + "args": { + "External id": 1419836,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013315.917, "dur": 11.563, + "args": { + "External id": 1419837,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 7740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535013452.506, "dur": 3415.172, + "args": { + "External id": 1419838,"Record function id": 0, "Ev Idx": 7741 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410535013478.338, "dur": 1257.532, + "args": { + "External id": 1419839,"Record function id": 0, "Ev Idx": 7742 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410535013496.435, "dur": 374.185, + "args": { + "External id": 1419840,"Record function id": 0, "Ev Idx": 7743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013598.234, "dur": 6.731, + "args": { + "External id": 1419841,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013609.113, "dur": 1.013, + "args": { + "External id": 1419842,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013612.608, "dur": 0.975, + "args": { + "External id": 1419843,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013615.745, "dur": 3.351, + "args": { + "External id": 1419844,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013621.196, "dur": 1.035, + "args": { + "External id": 1419845,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013623.961, "dur": 1.208, + "args": { + "External id": 1419846,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013627.000, "dur": 0.931, + "args": { + "External id": 1419847,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013631.987, "dur": 1.269, + "args": { + "External id": 1419848,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013635.111, "dur": 1.386, + "args": { + "External id": 1419849,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535013638.051, "dur": 0.776, + "args": { + "External id": 1419850,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535013659.781, "dur": 174.084, + "args": { + "External id": 1419851,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535013678.681, "dur": 149.764, + "args": { + "External id": 1419852,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535013697.137, "dur": 18.767, + "args": { + "External id": 1419853,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535013723.741, "dur": 74.935, + "args": { + "External id": 1419854,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 7757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535013726.679, "dur": 71.632, + "args": { + "External id": 1419855,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 7758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535013731.279, "dur": 9.031, + "args": { + "External id": 1419856,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535013742.278, "dur": 55.288, + "args": { + "External id": 1419857,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 7760 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.22", "pid": 2338710, "tid": 2379450, + "ts": 6410535013971.963, "dur": 754.762, + "args": { + "External id": 1419858,"Record function id": 0, "Ev Idx": 7761 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410535013991.026, "dur": 720.061, + "args": { + "External id": 1419859,"Record function id": 0, "Ev Idx": 7762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535014107.835, "dur": 8.459, + "args": { + "External id": 1419860,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535014135.808, "dur": 36.356, + "args": { + "External id": 1419861,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014141.680, "dur": 3.471, + "args": { + "External id": 1419862,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014146.990, "dur": 0.364, + "args": { + "External id": 1419863,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014149.020, "dur": 0.466, + "args": { + "External id": 1419864,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014152.517, "dur": 0.626, + "args": { + "External id": 1419865,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014155.053, "dur": 0.589, + "args": { + "External id": 1419866,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014156.863, "dur": 0.494, + "args": { + "External id": 1419867,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014160.360, "dur": 3.155, + "args": { + "External id": 1419868,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014164.490, "dur": 0.441, + "args": { + "External id": 1419869,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014166.757, "dur": 1.365, + "args": { + "External id": 1419870,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535014185.697, "dur": 52.289, + "args": { + "External id": 1419871,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535014277.655, "dur": 127.453, + "args": { + "External id": 1419872,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 7775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535014290.501, "dur": 3.866, + "args": { + "External id": 1419873,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535014300.522, "dur": 11.368, + "args": { + "External id": 1419874,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535014305.050, "dur": 6.384, + "args": { + "External id": 1419875,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 7778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014309.324, "dur": 0.520, + "args": { + "External id": 1419876,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535014319.745, "dur": 27.869, + "args": { + "External id": 1419877,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014322.060, "dur": 0.778, + "args": { + "External id": 1419878,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014324.784, "dur": 0.494, + "args": { + "External id": 1419879,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014326.440, "dur": 2.170, + "args": { + "External id": 1419880,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014330.350, "dur": 2.494, + "args": { + "External id": 1419881,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014334.311, "dur": 0.387, + "args": { + "External id": 1419882,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014337.829, "dur": 0.407, + "args": { + "External id": 1419883,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014339.530, "dur": 0.362, + "args": { + "External id": 1419884,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014341.511, "dur": 0.433, + "args": { + "External id": 1419885,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535014343.924, "dur": 0.313, + "args": { + "External id": 1419886,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535014361.244, "dur": 34.903, + "args": { + "External id": 1419887,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535014480.041, "dur": 142.027, + "args": { + "External id": 1419888,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 7791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535014514.825, "dur": 102.847, + "args": { + "External id": 1419889,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7792, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535014527.991, "dur": 84.894, + "args": { + "External id": 1419890,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 7793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535014644.789, "dur": 1.993, + "args": { + "External id": 1419891,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7794, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535014744.641, "dur": 2096.448, + "args": { + "External id": 1419892,"Sequence number": 15109119, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7795 + } + }, + { + "ph": "f", "id": 400, "pid": 2338710, "tid": 2379450, "ts": 6410535014744.641, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535014873.990, "dur": 121.905, + "args": { + "External id": 1419893,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 7796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535015049.903, "dur": 95.270, + "args": { + "External id": 1419894,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 7797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535015169.976, "dur": 68.289, + "args": { + "External id": 1419895,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 7798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535015250.025, "dur": 38.690, + "args": { + "External id": 1419896,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535015298.999, "dur": 36.836, + "args": { + "External id": 1419897,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535015343.886, "dur": 32.197, + "args": { + "External id": 1419898,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535015384.863, "dur": 54.604, + "args": { + "External id": 1419899,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535015476.790, "dur": 31.158, + "args": { + "External id": 1419900,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 7803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535015532.613, "dur": 31.912, + "args": { + "External id": 1419901,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535015591.829, "dur": 22.788, + "args": { + "External id": 1419902,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535015631.869, "dur": 18.078, + "args": { + "External id": 1419903,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535015658.818, "dur": 48.516, + "args": { + "External id": 1419904,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535015711.254, "dur": 36.698, + "args": { + "External id": 1419905,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535015784.786, "dur": 360.976, + "args": { + "External id": 1419906,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535015898.706, "dur": 8.794, + "args": { + "External id": 1419907,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535015909.963, "dur": 3.926, + "args": { + "External id": 1419908,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535015915.580, "dur": 2.480, + "args": { + "External id": 1419909,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535015918.975, "dur": 4.046, + "args": { + "External id": 1419910,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535015977.615, "dur": 5.540, + "args": { + "External id": 1419911,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535015979.619, "dur": 3.353, + "args": { + "External id": 1419912,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535015988.017, "dur": 40.753, + "args": { + "External id": 1419913,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535015994.442, "dur": 2.118, + "args": { + "External id": 1419914,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535016030.760, "dur": 1.732, + "args": { + "External id": 1419915,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535016031.851, "dur": 0.529, + "args": { + "External id": 1419916,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535016033.527, "dur": 20.561, + "args": { + "External id": 1419917,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535016036.127, "dur": 2.910, + "args": { + "External id": 1419918,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535016193.817, "dur": 35.916, + "args": { + "External id": 1419919,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535016252.730, "dur": 20.064, + "args": { + "External id": 1419920,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535016281.716, "dur": 58.478, + "args": { + "External id": 1419921,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535016347.971, "dur": 47.015, + "args": { + "External id": 1419922,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535016406.972, "dur": 47.226, + "args": { + "External id": 1419923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535016464.592, "dur": 38.433, + "args": { + "External id": 1419924,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535016511.373, "dur": 31.947, + "args": { + "External id": 1419925,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535016550.637, "dur": 33.604, + "args": { + "External id": 1419926,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535016610.836, "dur": 30.476, + "args": { + "External id": 1419927,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 7830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535016661.311, "dur": 31.795, + "args": { + "External id": 1419928,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535016712.068, "dur": 19.452, + "args": { + "External id": 1419929,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535016752.756, "dur": 17.417, + "args": { + "External id": 1419930,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535016786.839, "dur": 18.594, + "args": { + "External id": 1419931,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 7834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016892.997, "dur": 16.586, + "args": { + "External id": 1419932,"Record function id": 0, "Ev Idx": 7835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016896.539, "dur": 12.050, + "args": { + "External id": 1419933,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016901.395, "dur": 5.860, + "args": { + "External id": 1419934,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016902.988, "dur": 4.154, + "args": { + "External id": 1419935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016914.342, "dur": 5.924, + "args": { + "External id": 1419936,"Record function id": 0, "Ev Idx": 7839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016916.522, "dur": 3.140, + "args": { + "External id": 1419937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016917.334, "dur": 1.827, + "args": { + "External id": 1419938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016917.967, "dur": 1.064, + "args": { + "External id": 1419939,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016924.226, "dur": 7.123, + "args": { + "External id": 1419940,"Record function id": 0, "Ev Idx": 7843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016925.475, "dur": 5.374, + "args": { + "External id": 1419941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016926.444, "dur": 3.921, + "args": { + "External id": 1419942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016927.235, "dur": 3.009, + "args": { + "External id": 1419943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016935.076, "dur": 4.799, + "args": { + "External id": 1419944,"Record function id": 0, "Ev Idx": 7847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016936.760, "dur": 2.670, + "args": { + "External id": 1419945,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016937.532, "dur": 1.427, + "args": { + "External id": 1419946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016937.912, "dur": 0.970, + "args": { + "External id": 1419947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016943.543, "dur": 4.394, + "args": { + "External id": 1419948,"Record function id": 0, "Ev Idx": 7851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016944.892, "dur": 2.571, + "args": { + "External id": 1419949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016945.413, "dur": 1.420, + "args": { + "External id": 1419950,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016945.913, "dur": 0.838, + "args": { + "External id": 1419951,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016951.548, "dur": 4.987, + "args": { + "External id": 1419952,"Record function id": 0, "Ev Idx": 7855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016952.912, "dur": 3.118, + "args": { + "External id": 1419953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016953.495, "dur": 1.833, + "args": { + "External id": 1419954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016954.205, "dur": 1.038, + "args": { + "External id": 1419955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016960.168, "dur": 4.534, + "args": { + "External id": 1419956,"Record function id": 0, "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016961.515, "dur": 2.734, + "args": { + "External id": 1419957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016962.207, "dur": 1.342, + "args": { + "External id": 1419958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016962.682, "dur": 0.749, + "args": { + "External id": 1419959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016968.276, "dur": 6.973, + "args": { + "External id": 1419960,"Record function id": 0, "Ev Idx": 7863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016969.922, "dur": 4.863, + "args": { + "External id": 1419961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016970.589, "dur": 3.688, + "args": { + "External id": 1419962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016973.273, "dur": 0.870, + "args": { + "External id": 1419963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016978.890, "dur": 4.705, + "args": { + "External id": 1419964,"Record function id": 0, "Ev Idx": 7867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535016980.282, "dur": 2.832, + "args": { + "External id": 1419965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016981.171, "dur": 1.424, + "args": { + "External id": 1419966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535016981.721, "dur": 0.767, + "args": { + "External id": 1419967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535016988.577, "dur": 74656.114, + "args": { + "External id": 1419968,"Record function id": 0, "Sequence number": 15109118, "Fwd thread id": 1, "Ev Idx": 7871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535016990.343, "dur": 74642.693, + "args": { + "External id": 1419969,"Sequence number": 15109118, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7872 + } + }, + { + "ph": "f", "id": 401, "pid": 2338710, "tid": 2379450, "ts": 6410535016990.343, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410535017025.291, "dur": 85.616, + "args": { + "External id": 1419970,"Record function id": 0, "Ev Idx": 7873 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410535017122.023, "dur": 80.187, + "args": { + "External id": 1419971,"Record function id": 0, "Ev Idx": 7874 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 2338710, "tid": 2379450, + "ts": 6410535017208.756, "dur": 74415.349, + "args": { + "External id": 1419972,"Record function id": 0, "Ev Idx": 7875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535017315.723, "dur": 8.044, + "args": { + "External id": 1419973,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535017335.496, "dur": 8.516, + "args": { + "External id": 1419974,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535017361.200, "dur": 73085.332, + "args": { + "External id": 1419975,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535017377.772, "dur": 73052.721, + "args": { + "External id": 1419976,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535017511.288, "dur": 27.558, + "args": { + "External id": 1419977,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535017571.081, "dur": 72789.141, + "args": { + "External id": 1419978,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 7881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535017574.422, "dur": 72784.473, + "args": { + "External id": 1419979,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 7882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535017582.106, "dur": 14.422, + "args": { + "External id": 1419980,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535017598.777, "dur": 72754.015, + "args": { + "External id": 1419981,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 7884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535090571.310, "dur": 14.690, + "args": { + "External id": 1419982,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 7885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535090575.461, "dur": 10.178, + "args": { + "External id": 1419983,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535090622.522, "dur": 511.196, + "args": { + "External id": 1419984,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 7887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535090659.759, "dur": 467.108, + "args": { + "External id": 1419985,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7888, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535090674.442, "dur": 445.194, + "args": { + "External id": 1419986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 7889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535091163.067, "dur": 2.918, + "args": { + "External id": 1419987,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7890, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091240.996, "dur": 8.104, + "args": { + "External id": 1419988,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091264.299, "dur": 42.717, + "args": { + "External id": 1419989,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091320.076, "dur": 2.095, + "args": { + "External id": 1419990,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091328.661, "dur": 14.066, + "args": { + "External id": 1419991,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091349.853, "dur": 1.149, + "args": { + "External id": 1419992,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091363.407, "dur": 11.924, + "args": { + "External id": 1419993,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091383.567, "dur": 1.163, + "args": { + "External id": 1419994,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091389.425, "dur": 12.265, + "args": { + "External id": 1419995,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091407.501, "dur": 3.930, + "args": { + "External id": 1419996,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091431.528, "dur": 15.628, + "args": { + "External id": 1419997,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091455.768, "dur": 3.308, + "args": { + "External id": 1419998,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091464.306, "dur": 14.303, + "args": { + "External id": 1419999,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091486.743, "dur": 1.031, + "args": { + "External id": 1420000,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091491.773, "dur": 13.252, + "args": { + "External id": 1420001,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091510.008, "dur": 1.120, + "args": { + "External id": 1420002,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091516.081, "dur": 13.895, + "args": { + "External id": 1420003,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091535.169, "dur": 1.279, + "args": { + "External id": 1420004,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091540.868, "dur": 12.613, + "args": { + "External id": 1420005,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 7908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535091662.432, "dur": 3367.491, + "args": { + "External id": 1420006,"Record function id": 0, "Ev Idx": 7909 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410535091686.284, "dur": 1229.915, + "args": { + "External id": 1420007,"Record function id": 0, "Ev Idx": 7910 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410535091703.754, "dur": 402.679, + "args": { + "External id": 1420008,"Record function id": 0, "Ev Idx": 7911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091803.435, "dur": 4.774, + "args": { + "External id": 1420009,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091812.106, "dur": 0.852, + "args": { + "External id": 1420010,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091814.752, "dur": 1.046, + "args": { + "External id": 1420011,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091817.977, "dur": 3.187, + "args": { + "External id": 1420012,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091822.739, "dur": 1.333, + "args": { + "External id": 1420013,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091826.047, "dur": 1.457, + "args": { + "External id": 1420014,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091829.021, "dur": 0.757, + "args": { + "External id": 1420015,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091831.603, "dur": 1.072, + "args": { + "External id": 1420016,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091836.735, "dur": 0.993, + "args": { + "External id": 1420017,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535091839.472, "dur": 1.176, + "args": { + "External id": 1420018,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535091861.055, "dur": 167.766, + "args": { + "External id": 1420019,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535091880.061, "dur": 143.214, + "args": { + "External id": 1420020,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535091896.924, "dur": 15.341, + "args": { + "External id": 1420021,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535091917.208, "dur": 75.844, + "args": { + "External id": 1420022,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 7925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535091922.729, "dur": 69.963, + "args": { + "External id": 1420023,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 7926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535091926.969, "dur": 9.486, + "args": { + "External id": 1420024,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535091938.392, "dur": 53.317, + "args": { + "External id": 1420025,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 7928 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.21", "pid": 2338710, "tid": 2379450, + "ts": 6410535092211.421, "dur": 696.341, + "args": { + "External id": 1420026,"Record function id": 0, "Ev Idx": 7929 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410535092232.152, "dur": 661.552, + "args": { + "External id": 1420027,"Record function id": 0, "Ev Idx": 7930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535092305.143, "dur": 6.952, + "args": { + "External id": 1420028,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535092330.218, "dur": 35.750, + "args": { + "External id": 1420029,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092335.815, "dur": 3.252, + "args": { + "External id": 1420030,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092341.049, "dur": 0.302, + "args": { + "External id": 1420031,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092343.334, "dur": 0.348, + "args": { + "External id": 1420032,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092346.411, "dur": 0.307, + "args": { + "External id": 1420033,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092348.809, "dur": 0.390, + "args": { + "External id": 1420034,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092350.431, "dur": 0.458, + "args": { + "External id": 1420035,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092353.755, "dur": 3.202, + "args": { + "External id": 1420036,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092358.256, "dur": 0.413, + "args": { + "External id": 1420037,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092360.063, "dur": 1.700, + "args": { + "External id": 1420038,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535092381.497, "dur": 68.251, + "args": { + "External id": 1420039,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535092491.803, "dur": 130.122, + "args": { + "External id": 1420040,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 7943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535092504.662, "dur": 5.952, + "args": { + "External id": 1420041,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535092516.923, "dur": 12.217, + "args": { + "External id": 1420042,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535092521.954, "dur": 6.701, + "args": { + "External id": 1420043,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 7946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092525.820, "dur": 0.823, + "args": { + "External id": 1420044,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535092537.256, "dur": 28.686, + "args": { + "External id": 1420045,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092539.780, "dur": 0.588, + "args": { + "External id": 1420046,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092542.016, "dur": 1.462, + "args": { + "External id": 1420047,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092544.876, "dur": 0.489, + "args": { + "External id": 1420048,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092546.466, "dur": 3.058, + "args": { + "External id": 1420049,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092552.664, "dur": 0.385, + "args": { + "External id": 1420050,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092554.787, "dur": 0.546, + "args": { + "External id": 1420051,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092557.335, "dur": 0.390, + "args": { + "External id": 1420052,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092559.767, "dur": 0.508, + "args": { + "External id": 1420053,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535092561.993, "dur": 0.617, + "args": { + "External id": 1420054,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535092579.482, "dur": 33.130, + "args": { + "External id": 1420055,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535092676.150, "dur": 137.886, + "args": { + "External id": 1420056,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 7959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535092711.063, "dur": 99.005, + "args": { + "External id": 1420057,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7960, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535092722.686, "dur": 82.091, + "args": { + "External id": 1420058,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 7961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535092833.809, "dur": 2.254, + "args": { + "External id": 1420059,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7962, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535092934.155, "dur": 2068.261, + "args": { + "External id": 1420060,"Sequence number": 15109117, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7963 + } + }, + { + "ph": "f", "id": 402, "pid": 2338710, "tid": 2379450, "ts": 6410535092934.155, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535093102.104, "dur": 127.120, + "args": { + "External id": 1420061,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 7964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535093288.357, "dur": 48.044, + "args": { + "External id": 1420062,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 7965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535093357.458, "dur": 72.547, + "args": { + "External id": 1420063,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 7966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535093445.912, "dur": 43.065, + "args": { + "External id": 1420064,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535093499.450, "dur": 38.603, + "args": { + "External id": 1420065,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535093545.543, "dur": 32.806, + "args": { + "External id": 1420066,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535093586.283, "dur": 34.255, + "args": { + "External id": 1420067,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535093654.055, "dur": 28.838, + "args": { + "External id": 1420068,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 7971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535093709.978, "dur": 32.299, + "args": { + "External id": 1420069,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535093765.897, "dur": 23.889, + "args": { + "External id": 1420070,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535093809.259, "dur": 16.890, + "args": { + "External id": 1420071,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535093835.034, "dur": 43.201, + "args": { + "External id": 1420072,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535093882.047, "dur": 36.186, + "args": { + "External id": 1420073,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535093954.064, "dur": 367.864, + "args": { + "External id": 1420074,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535094106.306, "dur": 10.898, + "args": { + "External id": 1420075,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535094120.263, "dur": 2.976, + "args": { + "External id": 1420076,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535094124.481, "dur": 2.665, + "args": { + "External id": 1420077,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535094128.186, "dur": 4.164, + "args": { + "External id": 1420078,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535094193.896, "dur": 5.671, + "args": { + "External id": 1420079,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535094196.228, "dur": 3.173, + "args": { + "External id": 1420080,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535094202.069, "dur": 37.592, + "args": { + "External id": 1420081,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535094208.098, "dur": 2.035, + "args": { + "External id": 1420082,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535094241.596, "dur": 2.105, + "args": { + "External id": 1420083,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535094242.951, "dur": 0.635, + "args": { + "External id": 1420084,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535094246.774, "dur": 21.623, + "args": { + "External id": 1420085,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535094249.263, "dur": 3.717, + "args": { + "External id": 1420086,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535094368.154, "dur": 34.601, + "args": { + "External id": 1420087,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535094441.862, "dur": 23.632, + "args": { + "External id": 1420088,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535094477.093, "dur": 57.851, + "args": { + "External id": 1420089,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535094543.012, "dur": 45.631, + "args": { + "External id": 1420090,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535094601.269, "dur": 25.178, + "args": { + "External id": 1420091,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535094633.168, "dur": 35.633, + "args": { + "External id": 1420092,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535094677.332, "dur": 31.285, + "args": { + "External id": 1420093,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535094716.714, "dur": 33.956, + "args": { + "External id": 1420094,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535094776.399, "dur": 28.891, + "args": { + "External id": 1420095,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 7998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535094826.262, "dur": 30.388, + "args": { + "External id": 1420096,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535094875.996, "dur": 20.992, + "args": { + "External id": 1420097,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535094918.669, "dur": 16.340, + "args": { + "External id": 1420098,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535094949.886, "dur": 18.940, + "args": { + "External id": 1420099,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095054.424, "dur": 58.075, + "args": { + "External id": 1420100,"Record function id": 0, "Ev Idx": 8003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095096.788, "dur": 14.047, + "args": { + "External id": 1420101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095102.340, "dur": 6.754, + "args": { + "External id": 1420102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095104.302, "dur": 4.459, + "args": { + "External id": 1420103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095120.437, "dur": 6.930, + "args": { + "External id": 1420104,"Record function id": 0, "Ev Idx": 8007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095123.402, "dur": 3.471, + "args": { + "External id": 1420105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095124.201, "dur": 1.952, + "args": { + "External id": 1420106,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095124.981, "dur": 1.071, + "args": { + "External id": 1420107,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095131.336, "dur": 7.973, + "args": { + "External id": 1420108,"Record function id": 0, "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095133.032, "dur": 5.732, + "args": { + "External id": 1420109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095133.848, "dur": 4.376, + "args": { + "External id": 1420110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095134.868, "dur": 3.267, + "args": { + "External id": 1420111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095143.048, "dur": 5.597, + "args": { + "External id": 1420112,"Record function id": 0, "Ev Idx": 8015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095144.902, "dur": 3.097, + "args": { + "External id": 1420113,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095145.647, "dur": 1.759, + "args": { + "External id": 1420114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095146.309, "dur": 1.013, + "args": { + "External id": 1420115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095152.285, "dur": 5.155, + "args": { + "External id": 1420116,"Record function id": 0, "Ev Idx": 8019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095153.990, "dur": 2.923, + "args": { + "External id": 1420117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095154.578, "dur": 1.623, + "args": { + "External id": 1420118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095155.260, "dur": 0.856, + "args": { + "External id": 1420119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095161.087, "dur": 6.585, + "args": { + "External id": 1420120,"Record function id": 0, "Ev Idx": 8023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095162.628, "dur": 4.562, + "args": { + "External id": 1420121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095163.188, "dur": 3.464, + "args": { + "External id": 1420122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095165.720, "dur": 0.822, + "args": { + "External id": 1420123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095171.468, "dur": 4.830, + "args": { + "External id": 1420124,"Record function id": 0, "Ev Idx": 8027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095173.093, "dur": 2.702, + "args": { + "External id": 1420125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095173.690, "dur": 1.407, + "args": { + "External id": 1420126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095174.281, "dur": 0.733, + "args": { + "External id": 1420127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095179.951, "dur": 5.385, + "args": { + "External id": 1420128,"Record function id": 0, "Ev Idx": 8031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095181.596, "dur": 3.264, + "args": { + "External id": 1420129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095182.315, "dur": 1.857, + "args": { + "External id": 1420130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095182.976, "dur": 1.072, + "args": { + "External id": 1420131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095188.969, "dur": 5.122, + "args": { + "External id": 1420132,"Record function id": 0, "Ev Idx": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535095190.312, "dur": 3.271, + "args": { + "External id": 1420133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095191.027, "dur": 1.655, + "args": { + "External id": 1420134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535095191.822, "dur": 0.777, + "args": { + "External id": 1420135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535095199.096, "dur": 64790.155, + "args": { + "External id": 1420136,"Record function id": 0, "Sequence number": 15109116, "Fwd thread id": 1, "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535095200.426, "dur": 64777.781, + "args": { + "External id": 1420137,"Sequence number": 15109116, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8040 + } + }, + { + "ph": "f", "id": 403, "pid": 2338710, "tid": 2379450, "ts": 6410535095200.426, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410535095238.903, "dur": 45.821, + "args": { + "External id": 1420138,"Record function id": 0, "Ev Idx": 8041 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410535095294.247, "dur": 75.404, + "args": { + "External id": 1420139,"Record function id": 0, "Ev Idx": 8042 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 2338710, "tid": 2379450, + "ts": 6410535095376.908, "dur": 64592.026, + "args": { + "External id": 1420140,"Record function id": 0, "Ev Idx": 8043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535095503.931, "dur": 8.504, + "args": { + "External id": 1420141,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535095526.852, "dur": 8.070, + "args": { + "External id": 1420142,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535095553.870, "dur": 63320.187, + "args": { + "External id": 1420143,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535095570.522, "dur": 63287.928, + "args": { + "External id": 1420144,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535095684.131, "dur": 23.892, + "args": { + "External id": 1420145,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535095734.970, "dur": 63067.303, + "args": { + "External id": 1420146,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535095737.937, "dur": 63063.397, + "args": { + "External id": 1420147,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535095744.344, "dur": 11.385, + "args": { + "External id": 1420148,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535095760.924, "dur": 63036.816, + "args": { + "External id": 1420149,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535158996.993, "dur": 13.901, + "args": { + "External id": 1420150,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535159001.098, "dur": 9.242, + "args": { + "External id": 1420151,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159046.380, "dur": 473.608, + "args": { + "External id": 1420152,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535159115.207, "dur": 397.818, + "args": { + "External id": 1420153,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8056, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535159131.209, "dur": 374.858, + "args": { + "External id": 1420154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535159549.354, "dur": 3.013, + "args": { + "External id": 1420155,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8058, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159627.981, "dur": 7.898, + "args": { + "External id": 1420156,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159651.641, "dur": 41.553, + "args": { + "External id": 1420157,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159705.804, "dur": 1.895, + "args": { + "External id": 1420158,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159714.833, "dur": 14.378, + "args": { + "External id": 1420159,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159735.484, "dur": 1.104, + "args": { + "External id": 1420160,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159741.992, "dur": 11.839, + "args": { + "External id": 1420161,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159760.007, "dur": 1.146, + "args": { + "External id": 1420162,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159765.377, "dur": 12.318, + "args": { + "External id": 1420163,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159786.016, "dur": 3.837, + "args": { + "External id": 1420164,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159794.258, "dur": 11.703, + "args": { + "External id": 1420165,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159811.252, "dur": 1.688, + "args": { + "External id": 1420166,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159817.174, "dur": 11.972, + "args": { + "External id": 1420167,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159833.860, "dur": 1.070, + "args": { + "External id": 1420168,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159839.115, "dur": 11.334, + "args": { + "External id": 1420169,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159858.251, "dur": 0.973, + "args": { + "External id": 1420170,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159863.550, "dur": 11.618, + "args": { + "External id": 1420171,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535159880.328, "dur": 1.200, + "args": { + "External id": 1420172,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535159886.241, "dur": 12.613, + "args": { + "External id": 1420173,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535160005.512, "dur": 3475.370, + "args": { + "External id": 1420174,"Record function id": 0, "Ev Idx": 8077 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410535160029.848, "dur": 1308.956, + "args": { + "External id": 1420175,"Record function id": 0, "Ev Idx": 8078 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410535160047.564, "dur": 455.471, + "args": { + "External id": 1420176,"Record function id": 0, "Ev Idx": 8079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160194.244, "dur": 6.125, + "args": { + "External id": 1420177,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160204.744, "dur": 0.912, + "args": { + "External id": 1420178,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160208.227, "dur": 1.193, + "args": { + "External id": 1420179,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160211.355, "dur": 3.765, + "args": { + "External id": 1420180,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160217.588, "dur": 1.094, + "args": { + "External id": 1420181,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160222.753, "dur": 1.045, + "args": { + "External id": 1420182,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160225.802, "dur": 0.885, + "args": { + "External id": 1420183,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160228.460, "dur": 1.320, + "args": { + "External id": 1420184,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160231.789, "dur": 0.969, + "args": { + "External id": 1420185,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535160236.809, "dur": 1.210, + "args": { + "External id": 1420186,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535160260.635, "dur": 197.800, + "args": { + "External id": 1420187,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535160282.046, "dur": 169.933, + "args": { + "External id": 1420188,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535160300.644, "dur": 16.450, + "args": { + "External id": 1420189,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535160322.102, "dur": 76.323, + "args": { + "External id": 1420190,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535160324.835, "dur": 73.225, + "args": { + "External id": 1420191,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160328.957, "dur": 8.263, + "args": { + "External id": 1420192,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535160339.082, "dur": 58.160, + "args": { + "External id": 1420193,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.20", "pid": 2338710, "tid": 2379450, + "ts": 6410535160607.368, "dur": 723.430, + "args": { + "External id": 1420194,"Record function id": 0, "Ev Idx": 8097 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410535160626.616, "dur": 689.189, + "args": { + "External id": 1420195,"Record function id": 0, "Ev Idx": 8098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535160699.529, "dur": 6.514, + "args": { + "External id": 1420196,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535160725.948, "dur": 36.900, + "args": { + "External id": 1420197,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160731.460, "dur": 1.884, + "args": { + "External id": 1420198,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160735.737, "dur": 2.259, + "args": { + "External id": 1420199,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160739.770, "dur": 0.590, + "args": { + "External id": 1420200,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160741.950, "dur": 0.616, + "args": { + "External id": 1420201,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160745.870, "dur": 0.500, + "args": { + "External id": 1420202,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160748.074, "dur": 0.830, + "args": { + "External id": 1420203,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160750.039, "dur": 3.327, + "args": { + "External id": 1420204,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160756.635, "dur": 0.569, + "args": { + "External id": 1420205,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160758.343, "dur": 0.712, + "args": { + "External id": 1420206,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535160775.666, "dur": 49.159, + "args": { + "External id": 1420207,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535160860.843, "dur": 130.331, + "args": { + "External id": 1420208,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535160872.931, "dur": 4.032, + "args": { + "External id": 1420209,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535160883.372, "dur": 13.345, + "args": { + "External id": 1420210,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535160889.446, "dur": 6.784, + "args": { + "External id": 1420211,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160893.716, "dur": 0.892, + "args": { + "External id": 1420212,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535160903.958, "dur": 29.578, + "args": { + "External id": 1420213,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160906.897, "dur": 0.623, + "args": { + "External id": 1420214,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160910.455, "dur": 0.459, + "args": { + "External id": 1420215,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160912.738, "dur": 0.409, + "args": { + "External id": 1420216,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160914.425, "dur": 3.571, + "args": { + "External id": 1420217,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160919.867, "dur": 0.327, + "args": { + "External id": 1420218,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160921.537, "dur": 0.414, + "args": { + "External id": 1420219,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160925.549, "dur": 0.368, + "args": { + "External id": 1420220,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160927.552, "dur": 0.297, + "args": { + "External id": 1420221,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535160929.700, "dur": 0.397, + "args": { + "External id": 1420222,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535160947.704, "dur": 34.578, + "args": { + "External id": 1420223,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535161042.264, "dur": 184.574, + "args": { + "External id": 1420224,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535161115.550, "dur": 106.546, + "args": { + "External id": 1420225,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8128, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535161128.444, "dur": 88.649, + "args": { + "External id": 1420226,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535161248.481, "dur": 2.283, + "args": { + "External id": 1420227,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8130, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535161346.614, "dur": 2105.286, + "args": { + "External id": 1420228,"Sequence number": 15109115, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8131 + } + }, + { + "ph": "f", "id": 404, "pid": 2338710, "tid": 2379450, "ts": 6410535161346.614, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535161498.755, "dur": 125.399, + "args": { + "External id": 1420229,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535161683.142, "dur": 49.555, + "args": { + "External id": 1420230,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535161753.908, "dur": 59.960, + "args": { + "External id": 1420231,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535161826.878, "dur": 36.965, + "args": { + "External id": 1420232,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535161873.660, "dur": 36.845, + "args": { + "External id": 1420233,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535161918.800, "dur": 32.546, + "args": { + "External id": 1420234,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535161959.211, "dur": 32.434, + "args": { + "External id": 1420235,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535162023.425, "dur": 25.581, + "args": { + "External id": 1420236,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535162117.043, "dur": 37.102, + "args": { + "External id": 1420237,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535162185.372, "dur": 23.943, + "args": { + "External id": 1420238,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535162227.527, "dur": 17.814, + "args": { + "External id": 1420239,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535162255.945, "dur": 50.315, + "args": { + "External id": 1420240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535162310.546, "dur": 38.669, + "args": { + "External id": 1420241,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535162385.184, "dur": 339.957, + "args": { + "External id": 1420242,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535162518.793, "dur": 9.907, + "args": { + "External id": 1420243,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535162531.435, "dur": 3.014, + "args": { + "External id": 1420244,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535162535.793, "dur": 2.056, + "args": { + "External id": 1420245,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535162538.984, "dur": 3.590, + "args": { + "External id": 1420246,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535162601.174, "dur": 7.575, + "args": { + "External id": 1420247,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535162605.386, "dur": 3.182, + "args": { + "External id": 1420248,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535162611.158, "dur": 40.548, + "args": { + "External id": 1420249,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535162620.555, "dur": 1.852, + "args": { + "External id": 1420250,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535162653.327, "dur": 1.935, + "args": { + "External id": 1420251,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535162654.489, "dur": 0.637, + "args": { + "External id": 1420252,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535162656.382, "dur": 19.967, + "args": { + "External id": 1420253,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535162658.585, "dur": 2.898, + "args": { + "External id": 1420254,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535162771.160, "dur": 34.985, + "args": { + "External id": 1420255,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535162829.764, "dur": 18.922, + "args": { + "External id": 1420256,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535162858.341, "dur": 54.345, + "args": { + "External id": 1420257,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535162920.781, "dur": 44.073, + "args": { + "External id": 1420258,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535162977.351, "dur": 24.161, + "args": { + "External id": 1420259,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535163008.614, "dur": 35.845, + "args": { + "External id": 1420260,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535163052.869, "dur": 74.447, + "args": { + "External id": 1420261,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535163140.098, "dur": 36.911, + "args": { + "External id": 1420262,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535163206.005, "dur": 28.295, + "args": { + "External id": 1420263,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535163255.296, "dur": 30.605, + "args": { + "External id": 1420264,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535163306.548, "dur": 19.111, + "args": { + "External id": 1420265,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535163346.895, "dur": 15.753, + "args": { + "External id": 1420266,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535163380.237, "dur": 18.523, + "args": { + "External id": 1420267,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163507.518, "dur": 18.125, + "args": { + "External id": 1420268,"Record function id": 0, "Ev Idx": 8171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163511.667, "dur": 12.881, + "args": { + "External id": 1420269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163516.954, "dur": 6.422, + "args": { + "External id": 1420270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163518.639, "dur": 4.560, + "args": { + "External id": 1420271,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163530.369, "dur": 5.231, + "args": { + "External id": 1420272,"Record function id": 0, "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163532.170, "dur": 2.933, + "args": { + "External id": 1420273,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163532.849, "dur": 1.729, + "args": { + "External id": 1420274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163533.482, "dur": 0.977, + "args": { + "External id": 1420275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163539.635, "dur": 8.010, + "args": { + "External id": 1420276,"Record function id": 0, "Ev Idx": 8179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163541.116, "dur": 5.999, + "args": { + "External id": 1420277,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163541.979, "dur": 4.451, + "args": { + "External id": 1420278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163542.985, "dur": 3.304, + "args": { + "External id": 1420279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163551.412, "dur": 5.263, + "args": { + "External id": 1420280,"Record function id": 0, "Ev Idx": 8183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163552.962, "dur": 3.223, + "args": { + "External id": 1420281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163553.769, "dur": 1.918, + "args": { + "External id": 1420282,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163554.386, "dur": 1.176, + "args": { + "External id": 1420283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163560.247, "dur": 4.580, + "args": { + "External id": 1420284,"Record function id": 0, "Ev Idx": 8187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163561.731, "dur": 2.627, + "args": { + "External id": 1420285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163562.485, "dur": 1.275, + "args": { + "External id": 1420286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163562.825, "dur": 0.844, + "args": { + "External id": 1420287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163568.536, "dur": 42.027, + "args": { + "External id": 1420288,"Record function id": 0, "Ev Idx": 8191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163604.317, "dur": 5.548, + "args": { + "External id": 1420289,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163605.205, "dur": 3.920, + "args": { + "External id": 1420290,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163608.139, "dur": 0.862, + "args": { + "External id": 1420291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163614.877, "dur": 4.267, + "args": { + "External id": 1420292,"Record function id": 0, "Ev Idx": 8195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163616.288, "dur": 2.380, + "args": { + "External id": 1420293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163617.009, "dur": 1.123, + "args": { + "External id": 1420294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163617.349, "dur": 0.676, + "args": { + "External id": 1420295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163623.044, "dur": 4.495, + "args": { + "External id": 1420296,"Record function id": 0, "Ev Idx": 8199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163624.360, "dur": 2.675, + "args": { + "External id": 1420297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163624.929, "dur": 1.542, + "args": { + "External id": 1420298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163625.519, "dur": 0.862, + "args": { + "External id": 1420299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163631.244, "dur": 3.998, + "args": { + "External id": 1420300,"Record function id": 0, "Ev Idx": 8203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535163632.299, "dur": 2.470, + "args": { + "External id": 1420301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163632.818, "dur": 1.311, + "args": { + "External id": 1420302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535163633.226, "dur": 0.776, + "args": { + "External id": 1420303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535163639.833, "dur": 61093.022, + "args": { + "External id": 1420304,"Record function id": 0, "Sequence number": 15109114, "Fwd thread id": 1, "Ev Idx": 8207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535163641.761, "dur": 61079.170, + "args": { + "External id": 1420305,"Sequence number": 15109114, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8208 + } + }, + { + "ph": "f", "id": 405, "pid": 2338710, "tid": 2379450, "ts": 6410535163641.761, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410535163678.090, "dur": 46.649, + "args": { + "External id": 1420306,"Record function id": 0, "Ev Idx": 8209 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410535163734.930, "dur": 75.775, + "args": { + "External id": 1420307,"Record function id": 0, "Ev Idx": 8210 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 2338710, "tid": 2379450, + "ts": 6410535163817.934, "dur": 60893.036, + "args": { + "External id": 1420308,"Record function id": 0, "Ev Idx": 8211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535163925.976, "dur": 8.633, + "args": { + "External id": 1420309,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535163945.730, "dur": 7.726, + "args": { + "External id": 1420310,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535163972.878, "dur": 59656.675, + "args": { + "External id": 1420311,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535163991.930, "dur": 59621.593, + "args": { + "External id": 1420312,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535164158.226, "dur": 30.136, + "args": { + "External id": 1420313,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535164213.712, "dur": 59353.529, + "args": { + "External id": 1420314,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535164217.165, "dur": 59348.771, + "args": { + "External id": 1420315,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535164222.397, "dur": 19.484, + "args": { + "External id": 1420316,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535164244.457, "dur": 59317.317, + "args": { + "External id": 1420317,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535223777.790, "dur": 15.304, + "args": { + "External id": 1420318,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535223782.164, "dur": 10.416, + "args": { + "External id": 1420319,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535223834.055, "dur": 390.167, + "args": { + "External id": 1420320,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535223870.105, "dur": 347.614, + "args": { + "External id": 1420321,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8224, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535223884.977, "dur": 325.563, + "args": { + "External id": 1420322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535224253.408, "dur": 2.907, + "args": { + "External id": 1420323,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8226, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224329.534, "dur": 7.973, + "args": { + "External id": 1420324,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224353.130, "dur": 43.159, + "args": { + "External id": 1420325,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224408.256, "dur": 1.744, + "args": { + "External id": 1420326,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224434.761, "dur": 20.608, + "args": { + "External id": 1420327,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224464.219, "dur": 1.622, + "args": { + "External id": 1420328,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224471.742, "dur": 13.828, + "args": { + "External id": 1420329,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224491.561, "dur": 1.075, + "args": { + "External id": 1420330,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224498.027, "dur": 14.051, + "args": { + "External id": 1420331,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224517.554, "dur": 3.222, + "args": { + "External id": 1420332,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224525.325, "dur": 13.249, + "args": { + "External id": 1420333,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224543.803, "dur": 1.698, + "args": { + "External id": 1420334,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224552.279, "dur": 14.366, + "args": { + "External id": 1420335,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224571.614, "dur": 1.242, + "args": { + "External id": 1420336,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224577.293, "dur": 12.811, + "args": { + "External id": 1420337,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224594.564, "dur": 0.984, + "args": { + "External id": 1420338,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224600.771, "dur": 14.124, + "args": { + "External id": 1420339,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535224621.790, "dur": 0.887, + "args": { + "External id": 1420340,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535224627.022, "dur": 12.192, + "args": { + "External id": 1420341,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535224750.961, "dur": 3476.107, + "args": { + "External id": 1420342,"Record function id": 0, "Ev Idx": 8245 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410535224774.745, "dur": 1271.217, + "args": { + "External id": 1420343,"Record function id": 0, "Ev Idx": 8246 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410535224794.550, "dur": 431.244, + "args": { + "External id": 1420344,"Record function id": 0, "Ev Idx": 8247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224895.347, "dur": 4.769, + "args": { + "External id": 1420345,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224904.296, "dur": 0.914, + "args": { + "External id": 1420346,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224907.368, "dur": 1.193, + "args": { + "External id": 1420347,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224911.191, "dur": 3.186, + "args": { + "External id": 1420348,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224916.548, "dur": 0.965, + "args": { + "External id": 1420349,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224919.124, "dur": 1.145, + "args": { + "External id": 1420350,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224922.395, "dur": 1.030, + "args": { + "External id": 1420351,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224927.158, "dur": 1.167, + "args": { + "External id": 1420352,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224930.033, "dur": 0.748, + "args": { + "External id": 1420353,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535224932.802, "dur": 1.519, + "args": { + "External id": 1420354,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535224954.695, "dur": 228.667, + "args": { + "External id": 1420355,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535224977.528, "dur": 198.924, + "args": { + "External id": 1420356,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535224998.906, "dur": 17.077, + "args": { + "External id": 1420357,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535225020.658, "dur": 122.788, + "args": { + "External id": 1420358,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535225026.847, "dur": 116.129, + "args": { + "External id": 1420359,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225031.377, "dur": 8.344, + "args": { + "External id": 1420360,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535225041.709, "dur": 99.742, + "args": { + "External id": 1420361,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8264 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.19", "pid": 2338710, "tid": 2379450, + "ts": 6410535225332.245, "dur": 705.130, + "args": { + "External id": 1420362,"Record function id": 0, "Ev Idx": 8265 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410535225353.180, "dur": 668.056, + "args": { + "External id": 1420363,"Record function id": 0, "Ev Idx": 8266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535225445.977, "dur": 7.917, + "args": { + "External id": 1420364,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535225473.449, "dur": 31.934, + "args": { + "External id": 1420365,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225479.097, "dur": 2.183, + "args": { + "External id": 1420366,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225483.323, "dur": 1.851, + "args": { + "External id": 1420367,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225486.478, "dur": 0.476, + "args": { + "External id": 1420368,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225487.745, "dur": 0.461, + "args": { + "External id": 1420369,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225490.601, "dur": 0.505, + "args": { + "External id": 1420370,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225491.934, "dur": 0.407, + "args": { + "External id": 1420371,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225494.050, "dur": 2.260, + "args": { + "External id": 1420372,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225498.710, "dur": 0.433, + "args": { + "External id": 1420373,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225500.751, "dur": 0.495, + "args": { + "External id": 1420374,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535225518.981, "dur": 51.252, + "args": { + "External id": 1420375,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535225607.857, "dur": 129.627, + "args": { + "External id": 1420376,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535225620.887, "dur": 3.832, + "args": { + "External id": 1420377,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535225630.670, "dur": 11.646, + "args": { + "External id": 1420378,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535225635.564, "dur": 6.259, + "args": { + "External id": 1420379,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225639.632, "dur": 0.681, + "args": { + "External id": 1420380,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535225654.824, "dur": 26.080, + "args": { + "External id": 1420381,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225656.889, "dur": 0.641, + "args": { + "External id": 1420382,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225660.203, "dur": 0.400, + "args": { + "External id": 1420383,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225662.063, "dur": 0.538, + "args": { + "External id": 1420384,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225663.790, "dur": 3.727, + "args": { + "External id": 1420385,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225668.853, "dur": 0.457, + "args": { + "External id": 1420386,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225670.503, "dur": 0.555, + "args": { + "External id": 1420387,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225673.887, "dur": 0.276, + "args": { + "External id": 1420388,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225675.296, "dur": 0.394, + "args": { + "External id": 1420389,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535225676.918, "dur": 0.547, + "args": { + "External id": 1420390,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535225693.425, "dur": 34.776, + "args": { + "External id": 1420391,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535225794.010, "dur": 144.278, + "args": { + "External id": 1420392,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535225831.933, "dur": 102.248, + "args": { + "External id": 1420393,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8296, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535225842.832, "dur": 86.669, + "args": { + "External id": 1420394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535225958.401, "dur": 1.970, + "args": { + "External id": 1420395,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8298, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535226055.272, "dur": 2141.638, + "args": { + "External id": 1420396,"Sequence number": 15109113, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8299 + } + }, + { + "ph": "f", "id": 406, "pid": 2338710, "tid": 2379450, "ts": 6410535226055.272, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535226230.790, "dur": 124.786, + "args": { + "External id": 1420397,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535226410.189, "dur": 67.296, + "args": { + "External id": 1420398,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535226502.281, "dur": 64.504, + "args": { + "External id": 1420399,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535226579.631, "dur": 38.581, + "args": { + "External id": 1420400,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535226628.046, "dur": 37.478, + "args": { + "External id": 1420401,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535226672.991, "dur": 33.050, + "args": { + "External id": 1420402,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535226715.096, "dur": 32.981, + "args": { + "External id": 1420403,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535226779.505, "dur": 28.296, + "args": { + "External id": 1420404,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535226832.341, "dur": 31.803, + "args": { + "External id": 1420405,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535226891.049, "dur": 20.537, + "args": { + "External id": 1420406,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535226929.134, "dur": 16.032, + "args": { + "External id": 1420407,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535226955.001, "dur": 40.785, + "args": { + "External id": 1420408,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535227000.239, "dur": 37.052, + "args": { + "External id": 1420409,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535227113.550, "dur": 352.649, + "args": { + "External id": 1420410,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535227222.363, "dur": 10.452, + "args": { + "External id": 1420411,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535227235.950, "dur": 3.835, + "args": { + "External id": 1420412,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535227241.040, "dur": 2.486, + "args": { + "External id": 1420413,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535227244.530, "dur": 2.736, + "args": { + "External id": 1420414,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535227300.243, "dur": 15.964, + "args": { + "External id": 1420415,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535227305.054, "dur": 10.212, + "args": { + "External id": 1420416,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535227320.186, "dur": 42.046, + "args": { + "External id": 1420417,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535227329.031, "dur": 2.411, + "args": { + "External id": 1420418,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535227364.513, "dur": 2.205, + "args": { + "External id": 1420419,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535227365.822, "dur": 0.779, + "args": { + "External id": 1420420,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535227367.474, "dur": 17.833, + "args": { + "External id": 1420421,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535227369.835, "dur": 3.001, + "args": { + "External id": 1420422,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535227520.887, "dur": 36.894, + "args": { + "External id": 1420423,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535227590.827, "dur": 18.660, + "args": { + "External id": 1420424,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535227619.591, "dur": 59.063, + "args": { + "External id": 1420425,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535227687.167, "dur": 45.985, + "args": { + "External id": 1420426,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535227744.729, "dur": 26.475, + "args": { + "External id": 1420427,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535227777.798, "dur": 35.838, + "args": { + "External id": 1420428,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535227821.825, "dur": 32.733, + "args": { + "External id": 1420429,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535227863.169, "dur": 33.332, + "args": { + "External id": 1420430,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535227921.558, "dur": 27.253, + "args": { + "External id": 1420431,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535227969.934, "dur": 29.532, + "args": { + "External id": 1420432,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535228019.474, "dur": 20.234, + "args": { + "External id": 1420433,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535228096.952, "dur": 23.392, + "args": { + "External id": 1420434,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535228141.632, "dur": 18.596, + "args": { + "External id": 1420435,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228252.286, "dur": 17.685, + "args": { + "External id": 1420436,"Record function id": 0, "Ev Idx": 8339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228256.449, "dur": 12.391, + "args": { + "External id": 1420437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228261.315, "dur": 6.227, + "args": { + "External id": 1420438,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228263.062, "dur": 4.384, + "args": { + "External id": 1420439,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228274.443, "dur": 5.792, + "args": { + "External id": 1420440,"Record function id": 0, "Ev Idx": 8343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228276.088, "dur": 3.654, + "args": { + "External id": 1420441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228276.951, "dur": 2.161, + "args": { + "External id": 1420442,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228278.029, "dur": 0.993, + "args": { + "External id": 1420443,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228284.269, "dur": 5.122, + "args": { + "External id": 1420444,"Record function id": 0, "Ev Idx": 8347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228285.519, "dur": 3.349, + "args": { + "External id": 1420445,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228286.368, "dur": 1.906, + "args": { + "External id": 1420446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228287.345, "dur": 0.797, + "args": { + "External id": 1420447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228293.159, "dur": 4.793, + "args": { + "External id": 1420448,"Record function id": 0, "Ev Idx": 8351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228294.809, "dur": 2.675, + "args": { + "External id": 1420449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228295.535, "dur": 1.357, + "args": { + "External id": 1420450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228295.955, "dur": 0.810, + "args": { + "External id": 1420451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228301.601, "dur": 6.666, + "args": { + "External id": 1420452,"Record function id": 0, "Ev Idx": 8355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228302.908, "dur": 4.880, + "args": { + "External id": 1420453,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228303.586, "dur": 3.522, + "args": { + "External id": 1420454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228303.893, "dur": 3.133, + "args": { + "External id": 1420455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228312.071, "dur": 5.078, + "args": { + "External id": 1420456,"Record function id": 0, "Ev Idx": 8359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228313.399, "dur": 3.172, + "args": { + "External id": 1420457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228313.971, "dur": 1.950, + "args": { + "External id": 1420458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228314.616, "dur": 1.219, + "args": { + "External id": 1420459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228320.847, "dur": 4.416, + "args": { + "External id": 1420460,"Record function id": 0, "Ev Idx": 8363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228322.302, "dur": 2.412, + "args": { + "External id": 1420461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228322.901, "dur": 1.310, + "args": { + "External id": 1420462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228323.241, "dur": 0.859, + "args": { + "External id": 1420463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228328.926, "dur": 7.255, + "args": { + "External id": 1420464,"Record function id": 0, "Ev Idx": 8367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228330.408, "dur": 5.257, + "args": { + "External id": 1420465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228331.086, "dur": 3.867, + "args": { + "External id": 1420466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228334.060, "dur": 0.809, + "args": { + "External id": 1420467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228340.451, "dur": 5.184, + "args": { + "External id": 1420468,"Record function id": 0, "Ev Idx": 8371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535228342.066, "dur": 3.084, + "args": { + "External id": 1420469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228343.046, "dur": 1.562, + "args": { + "External id": 1420470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535228343.408, "dur": 1.119, + "args": { + "External id": 1420471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535228350.486, "dur": 61780.127, + "args": { + "External id": 1420472,"Record function id": 0, "Sequence number": 15109112, "Fwd thread id": 1, "Ev Idx": 8375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535228352.094, "dur": 61765.348, + "args": { + "External id": 1420473,"Sequence number": 15109112, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8376 + } + }, + { + "ph": "f", "id": 407, "pid": 2338710, "tid": 2379450, "ts": 6410535228352.094, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410535228386.513, "dur": 67.173, + "args": { + "External id": 1420474,"Record function id": 0, "Ev Idx": 8377 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410535228464.572, "dur": 78.739, + "args": { + "External id": 1420475,"Record function id": 0, "Ev Idx": 8378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 2338710, "tid": 2379450, + "ts": 6410535228549.936, "dur": 61557.090, + "args": { + "External id": 1420476,"Record function id": 0, "Ev Idx": 8379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535228656.576, "dur": 9.308, + "args": { + "External id": 1420477,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535228678.453, "dur": 5.526, + "args": { + "External id": 1420478,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535228702.015, "dur": 60189.530, + "args": { + "External id": 1420479,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535228720.876, "dur": 60153.957, + "args": { + "External id": 1420480,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535228825.577, "dur": 23.939, + "args": { + "External id": 1420481,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535228872.802, "dur": 59938.745, + "args": { + "External id": 1420482,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535228876.191, "dur": 59933.521, + "args": { + "External id": 1420483,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535228881.886, "dur": 12.167, + "args": { + "External id": 1420484,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535228896.546, "dur": 59907.284, + "args": { + "External id": 1420485,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535289019.259, "dur": 15.029, + "args": { + "External id": 1420486,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535289023.274, "dur": 10.560, + "args": { + "External id": 1420487,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289119.173, "dur": 485.122, + "args": { + "External id": 1420488,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535289156.843, "dur": 440.839, + "args": { + "External id": 1420489,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8392, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535289173.525, "dur": 416.650, + "args": { + "External id": 1420490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535289632.967, "dur": 2.958, + "args": { + "External id": 1420491,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8394, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289712.194, "dur": 10.233, + "args": { + "External id": 1420492,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289738.387, "dur": 42.708, + "args": { + "External id": 1420493,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289793.187, "dur": 2.210, + "args": { + "External id": 1420494,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289801.243, "dur": 16.659, + "args": { + "External id": 1420495,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289824.421, "dur": 1.214, + "args": { + "External id": 1420496,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289830.467, "dur": 12.853, + "args": { + "External id": 1420497,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289851.561, "dur": 0.970, + "args": { + "External id": 1420498,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289858.122, "dur": 12.625, + "args": { + "External id": 1420499,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289875.955, "dur": 0.898, + "args": { + "External id": 1420500,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289881.386, "dur": 11.396, + "args": { + "External id": 1420501,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289897.407, "dur": 1.875, + "args": { + "External id": 1420502,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289903.940, "dur": 12.576, + "args": { + "External id": 1420503,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289921.332, "dur": 1.041, + "args": { + "External id": 1420504,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289929.545, "dur": 11.459, + "args": { + "External id": 1420505,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289946.021, "dur": 0.840, + "args": { + "External id": 1420506,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289950.742, "dur": 11.640, + "args": { + "External id": 1420507,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535289966.797, "dur": 3.665, + "args": { + "External id": 1420508,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535289974.831, "dur": 13.014, + "args": { + "External id": 1420509,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535290150.454, "dur": 3386.542, + "args": { + "External id": 1420510,"Record function id": 0, "Ev Idx": 8413 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410535290176.243, "dur": 1279.969, + "args": { + "External id": 1420511,"Record function id": 0, "Ev Idx": 8414 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410535290194.868, "dur": 404.322, + "args": { + "External id": 1420512,"Record function id": 0, "Ev Idx": 8415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290298.211, "dur": 5.486, + "args": { + "External id": 1420513,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290307.697, "dur": 1.161, + "args": { + "External id": 1420514,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290311.447, "dur": 0.994, + "args": { + "External id": 1420515,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290315.143, "dur": 0.929, + "args": { + "External id": 1420516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290320.442, "dur": 1.054, + "args": { + "External id": 1420517,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290323.181, "dur": 1.306, + "args": { + "External id": 1420518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290326.457, "dur": 0.975, + "args": { + "External id": 1420519,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290329.439, "dur": 3.777, + "args": { + "External id": 1420520,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290337.619, "dur": 0.870, + "args": { + "External id": 1420521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535290340.600, "dur": 1.484, + "args": { + "External id": 1420522,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535290362.078, "dur": 195.726, + "args": { + "External id": 1420523,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535290382.210, "dur": 169.339, + "args": { + "External id": 1420524,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535290401.796, "dur": 32.763, + "args": { + "External id": 1420525,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535290439.878, "dur": 80.099, + "args": { + "External id": 1420526,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535290442.676, "dur": 76.751, + "args": { + "External id": 1420527,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290447.294, "dur": 6.999, + "args": { + "External id": 1420528,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535290459.018, "dur": 59.657, + "args": { + "External id": 1420529,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8432 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.18", "pid": 2338710, "tid": 2379450, + "ts": 6410535290703.513, "dur": 742.386, + "args": { + "External id": 1420530,"Record function id": 0, "Ev Idx": 8433 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410535290723.928, "dur": 686.148, + "args": { + "External id": 1420531,"Record function id": 0, "Ev Idx": 8434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535290795.223, "dur": 6.003, + "args": { + "External id": 1420532,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535290819.453, "dur": 34.109, + "args": { + "External id": 1420533,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290824.817, "dur": 2.327, + "args": { + "External id": 1420534,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290829.034, "dur": 1.956, + "args": { + "External id": 1420535,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290832.560, "dur": 3.118, + "args": { + "External id": 1420536,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290837.217, "dur": 0.532, + "args": { + "External id": 1420537,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290840.649, "dur": 0.488, + "args": { + "External id": 1420538,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290842.472, "dur": 0.693, + "args": { + "External id": 1420539,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290844.806, "dur": 0.377, + "args": { + "External id": 1420540,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290847.607, "dur": 0.651, + "args": { + "External id": 1420541,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290849.134, "dur": 0.431, + "args": { + "External id": 1420542,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535290866.173, "dur": 53.109, + "args": { + "External id": 1420543,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535290955.002, "dur": 172.470, + "args": { + "External id": 1420544,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535290966.948, "dur": 7.125, + "args": { + "External id": 1420545,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535290980.558, "dur": 12.975, + "args": { + "External id": 1420546,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535290985.338, "dur": 7.720, + "args": { + "External id": 1420547,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535290988.823, "dur": 2.615, + "args": { + "External id": 1420548,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535291001.471, "dur": 28.560, + "args": { + "External id": 1420549,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291003.652, "dur": 0.648, + "args": { + "External id": 1420550,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291006.124, "dur": 0.786, + "args": { + "External id": 1420551,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291008.584, "dur": 0.633, + "args": { + "External id": 1420552,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291010.686, "dur": 1.589, + "args": { + "External id": 1420553,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291014.014, "dur": 0.641, + "args": { + "External id": 1420554,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291015.931, "dur": 0.660, + "args": { + "External id": 1420555,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291019.668, "dur": 0.577, + "args": { + "External id": 1420556,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291021.773, "dur": 2.669, + "args": { + "External id": 1420557,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535291025.862, "dur": 0.602, + "args": { + "External id": 1420558,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535291042.219, "dur": 73.783, + "args": { + "External id": 1420559,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535291185.855, "dur": 138.212, + "args": { + "External id": 1420560,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535291218.922, "dur": 100.924, + "args": { + "External id": 1420561,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8464, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535291229.470, "dur": 85.592, + "args": { + "External id": 1420562,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535291345.805, "dur": 2.221, + "args": { + "External id": 1420563,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8466, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535291466.373, "dur": 2039.711, + "args": { + "External id": 1420564,"Sequence number": 15109111, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8467 + } + }, + { + "ph": "f", "id": 408, "pid": 2338710, "tid": 2379450, "ts": 6410535291466.373, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535291598.827, "dur": 122.884, + "args": { + "External id": 1420565,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535291771.814, "dur": 47.274, + "args": { + "External id": 1420566,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535291841.515, "dur": 56.306, + "args": { + "External id": 1420567,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535291909.286, "dur": 37.327, + "args": { + "External id": 1420568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535291954.033, "dur": 35.600, + "args": { + "External id": 1420569,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535292000.436, "dur": 30.688, + "args": { + "External id": 1420570,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535292042.688, "dur": 78.043, + "args": { + "External id": 1420571,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535292156.700, "dur": 27.817, + "args": { + "External id": 1420572,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535292206.883, "dur": 32.388, + "args": { + "External id": 1420573,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535292264.230, "dur": 21.732, + "args": { + "External id": 1420574,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535292306.134, "dur": 16.989, + "args": { + "External id": 1420575,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535292334.709, "dur": 45.833, + "args": { + "External id": 1420576,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535292385.212, "dur": 53.506, + "args": { + "External id": 1420577,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535292475.921, "dur": 314.720, + "args": { + "External id": 1420578,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535292592.001, "dur": 8.693, + "args": { + "External id": 1420579,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535292603.341, "dur": 7.205, + "args": { + "External id": 1420580,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535292611.565, "dur": 5.189, + "args": { + "External id": 1420581,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535292617.875, "dur": 2.777, + "args": { + "External id": 1420582,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535292669.983, "dur": 6.658, + "args": { + "External id": 1420583,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535292672.083, "dur": 4.364, + "args": { + "External id": 1420584,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535292678.791, "dur": 35.542, + "args": { + "External id": 1420585,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535292684.946, "dur": 2.385, + "args": { + "External id": 1420586,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535292716.687, "dur": 3.949, + "args": { + "External id": 1420587,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535292719.675, "dur": 0.828, + "args": { + "External id": 1420588,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535292725.208, "dur": 15.425, + "args": { + "External id": 1420589,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535292727.323, "dur": 0.835, + "args": { + "External id": 1420590,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535292835.656, "dur": 32.582, + "args": { + "External id": 1420591,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535292889.924, "dur": 17.162, + "args": { + "External id": 1420592,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535292916.219, "dur": 51.710, + "args": { + "External id": 1420593,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535292975.726, "dur": 44.476, + "args": { + "External id": 1420594,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535293030.898, "dur": 65.458, + "args": { + "External id": 1420595,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535293108.250, "dur": 41.363, + "args": { + "External id": 1420596,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535293158.710, "dur": 32.014, + "args": { + "External id": 1420597,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535293199.345, "dur": 33.545, + "args": { + "External id": 1420598,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535293262.298, "dur": 29.470, + "args": { + "External id": 1420599,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535293314.084, "dur": 28.028, + "args": { + "External id": 1420600,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535293362.717, "dur": 18.573, + "args": { + "External id": 1420601,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535293397.122, "dur": 16.568, + "args": { + "External id": 1420602,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535293450.192, "dur": 20.258, + "args": { + "External id": 1420603,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293562.508, "dur": 18.712, + "args": { + "External id": 1420604,"Record function id": 0, "Ev Idx": 8507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293566.433, "dur": 13.628, + "args": { + "External id": 1420605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293571.580, "dur": 7.300, + "args": { + "External id": 1420606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293573.223, "dur": 5.532, + "args": { + "External id": 1420607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293585.969, "dur": 6.047, + "args": { + "External id": 1420608,"Record function id": 0, "Ev Idx": 8511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293587.842, "dur": 3.599, + "args": { + "External id": 1420609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293588.711, "dur": 2.053, + "args": { + "External id": 1420610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293589.438, "dur": 1.165, + "args": { + "External id": 1420611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293595.957, "dur": 8.758, + "args": { + "External id": 1420612,"Record function id": 0, "Ev Idx": 8515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293600.572, "dur": 3.613, + "args": { + "External id": 1420613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293601.696, "dur": 2.003, + "args": { + "External id": 1420614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293602.655, "dur": 0.953, + "args": { + "External id": 1420615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293608.483, "dur": 5.280, + "args": { + "External id": 1420616,"Record function id": 0, "Ev Idx": 8519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293610.291, "dur": 3.003, + "args": { + "External id": 1420617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293610.863, "dur": 1.823, + "args": { + "External id": 1420618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293611.657, "dur": 0.920, + "args": { + "External id": 1420619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293617.339, "dur": 9.545, + "args": { + "External id": 1420620,"Record function id": 0, "Ev Idx": 8523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293619.235, "dur": 7.131, + "args": { + "External id": 1420621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293620.118, "dur": 5.680, + "args": { + "External id": 1420622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293622.818, "dur": 2.845, + "args": { + "External id": 1420623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293630.688, "dur": 4.587, + "args": { + "External id": 1420624,"Record function id": 0, "Ev Idx": 8527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293632.303, "dur": 2.500, + "args": { + "External id": 1420625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293632.921, "dur": 1.426, + "args": { + "External id": 1420626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293633.256, "dur": 0.969, + "args": { + "External id": 1420627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293638.938, "dur": 4.465, + "args": { + "External id": 1420628,"Record function id": 0, "Ev Idx": 8531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293640.405, "dur": 2.513, + "args": { + "External id": 1420629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293641.214, "dur": 1.232, + "args": { + "External id": 1420630,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293641.576, "dur": 0.780, + "args": { + "External id": 1420631,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293646.918, "dur": 15.022, + "args": { + "External id": 1420632,"Record function id": 0, "Ev Idx": 8535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293652.799, "dur": 8.642, + "args": { + "External id": 1420633,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293653.488, "dur": 7.281, + "args": { + "External id": 1420634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293659.889, "dur": 0.767, + "args": { + "External id": 1420635,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293665.612, "dur": 5.087, + "args": { + "External id": 1420636,"Record function id": 0, "Ev Idx": 8539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535293667.214, "dur": 3.025, + "args": { + "External id": 1420637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293668.217, "dur": 1.277, + "args": { + "External id": 1420638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535293668.686, "dur": 0.707, + "args": { + "External id": 1420639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535293675.449, "dur": 62514.585, + "args": { + "External id": 1420640,"Record function id": 0, "Sequence number": 15109110, "Fwd thread id": 1, "Ev Idx": 8543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535293684.872, "dur": 62492.468, + "args": { + "External id": 1420641,"Sequence number": 15109110, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8544 + } + }, + { + "ph": "f", "id": 409, "pid": 2338710, "tid": 2379450, "ts": 6410535293684.872, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410535293725.054, "dur": 46.332, + "args": { + "External id": 1420642,"Record function id": 0, "Ev Idx": 8545 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410535293783.970, "dur": 82.334, + "args": { + "External id": 1420643,"Record function id": 0, "Ev Idx": 8546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 2338710, "tid": 2379450, + "ts": 6410535293873.019, "dur": 62294.338, + "args": { + "External id": 1420644,"Record function id": 0, "Ev Idx": 8547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535293979.865, "dur": 8.623, + "args": { + "External id": 1420645,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535293999.226, "dur": 5.457, + "args": { + "External id": 1420646,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535294022.529, "dur": 60974.422, + "args": { + "External id": 1420647,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535294041.173, "dur": 60940.040, + "args": { + "External id": 1420648,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535294193.164, "dur": 23.312, + "args": { + "External id": 1420649,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535294241.576, "dur": 60691.920, + "args": { + "External id": 1420650,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535294244.771, "dur": 60687.312, + "args": { + "External id": 1420651,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535294263.299, "dur": 19.758, + "args": { + "External id": 1420652,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535294285.871, "dur": 60642.709, + "args": { + "External id": 1420653,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535355154.239, "dur": 14.540, + "args": { + "External id": 1420654,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535355158.180, "dur": 9.894, + "args": { + "External id": 1420655,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535355204.063, "dur": 457.102, + "args": { + "External id": 1420656,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535355241.877, "dur": 412.444, + "args": { + "External id": 1420657,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8560, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535355258.002, "dur": 389.130, + "args": { + "External id": 1420658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535355688.957, "dur": 2.838, + "args": { + "External id": 1420659,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8562, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535355763.978, "dur": 9.579, + "args": { + "External id": 1420660,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535355789.521, "dur": 41.298, + "args": { + "External id": 1420661,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535355843.671, "dur": 1.903, + "args": { + "External id": 1420662,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535355852.710, "dur": 16.825, + "args": { + "External id": 1420663,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535355876.727, "dur": 1.297, + "args": { + "External id": 1420664,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535355883.295, "dur": 13.718, + "args": { + "External id": 1420665,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535355904.888, "dur": 1.264, + "args": { + "External id": 1420666,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535355911.317, "dur": 14.294, + "args": { + "External id": 1420667,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535355931.306, "dur": 1.074, + "args": { + "External id": 1420668,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535355937.730, "dur": 13.514, + "args": { + "External id": 1420669,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535355956.078, "dur": 1.389, + "args": { + "External id": 1420670,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535355962.755, "dur": 13.707, + "args": { + "External id": 1420671,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535355983.925, "dur": 1.200, + "args": { + "External id": 1420672,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535355989.955, "dur": 13.078, + "args": { + "External id": 1420673,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356007.731, "dur": 1.109, + "args": { + "External id": 1420674,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535356014.216, "dur": 13.414, + "args": { + "External id": 1420675,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356032.180, "dur": 3.335, + "args": { + "External id": 1420676,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535356040.519, "dur": 51.221, + "args": { + "External id": 1420677,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535356209.169, "dur": 3500.922, + "args": { + "External id": 1420678,"Record function id": 0, "Ev Idx": 8581 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410535356234.817, "dur": 1289.420, + "args": { + "External id": 1420679,"Record function id": 0, "Ev Idx": 8582 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410535356254.625, "dur": 404.370, + "args": { + "External id": 1420680,"Record function id": 0, "Ev Idx": 8583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356362.701, "dur": 5.582, + "args": { + "External id": 1420681,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356371.935, "dur": 1.073, + "args": { + "External id": 1420682,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356375.191, "dur": 1.129, + "args": { + "External id": 1420683,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356378.651, "dur": 0.901, + "args": { + "External id": 1420684,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356381.393, "dur": 1.267, + "args": { + "External id": 1420685,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356384.352, "dur": 1.118, + "args": { + "External id": 1420686,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356387.378, "dur": 0.864, + "args": { + "External id": 1420687,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356390.100, "dur": 3.947, + "args": { + "External id": 1420688,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356397.969, "dur": 0.750, + "args": { + "External id": 1420689,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535356401.112, "dur": 1.254, + "args": { + "External id": 1420690,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535356440.279, "dur": 179.231, + "args": { + "External id": 1420691,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535356462.229, "dur": 151.258, + "args": { + "External id": 1420692,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535356482.543, "dur": 18.525, + "args": { + "External id": 1420693,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535356505.639, "dur": 78.220, + "args": { + "External id": 1420694,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535356511.220, "dur": 72.191, + "args": { + "External id": 1420695,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356515.470, "dur": 7.323, + "args": { + "External id": 1420696,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535356524.566, "dur": 58.040, + "args": { + "External id": 1420697,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8600 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.17", "pid": 2338710, "tid": 2379450, + "ts": 6410535356757.759, "dur": 756.355, + "args": { + "External id": 1420698,"Record function id": 0, "Ev Idx": 8601 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410535356778.116, "dur": 720.013, + "args": { + "External id": 1420699,"Record function id": 0, "Ev Idx": 8602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535356847.886, "dur": 5.807, + "args": { + "External id": 1420700,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535356872.102, "dur": 34.848, + "args": { + "External id": 1420701,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356877.722, "dur": 1.871, + "args": { + "External id": 1420702,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356881.905, "dur": 2.149, + "args": { + "External id": 1420703,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356885.753, "dur": 3.367, + "args": { + "External id": 1420704,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356890.362, "dur": 0.456, + "args": { + "External id": 1420705,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356893.813, "dur": 0.391, + "args": { + "External id": 1420706,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356895.292, "dur": 0.426, + "args": { + "External id": 1420707,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356897.359, "dur": 0.547, + "args": { + "External id": 1420708,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356900.506, "dur": 0.626, + "args": { + "External id": 1420709,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535356902.290, "dur": 0.556, + "args": { + "External id": 1420710,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535356919.662, "dur": 47.222, + "args": { + "External id": 1420711,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535357004.335, "dur": 186.503, + "args": { + "External id": 1420712,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535357016.467, "dur": 4.293, + "args": { + "External id": 1420713,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535357026.812, "dur": 14.173, + "args": { + "External id": 1420714,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535357031.874, "dur": 8.619, + "args": { + "External id": 1420715,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357035.831, "dur": 3.039, + "args": { + "External id": 1420716,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535357049.061, "dur": 74.433, + "args": { + "External id": 1420717,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357051.494, "dur": 0.780, + "args": { + "External id": 1420718,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357055.022, "dur": 43.738, + "args": { + "External id": 1420719,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357101.918, "dur": 0.855, + "args": { + "External id": 1420720,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357104.076, "dur": 1.567, + "args": { + "External id": 1420721,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357107.279, "dur": 0.475, + "args": { + "External id": 1420722,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357109.300, "dur": 0.427, + "args": { + "External id": 1420723,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357112.773, "dur": 0.381, + "args": { + "External id": 1420724,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357114.584, "dur": 2.785, + "args": { + "External id": 1420725,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535357118.663, "dur": 0.535, + "args": { + "External id": 1420726,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535357141.851, "dur": 38.957, + "args": { + "External id": 1420727,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535357247.936, "dur": 140.165, + "args": { + "External id": 1420728,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535357280.947, "dur": 103.104, + "args": { + "External id": 1420729,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8632, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535357292.374, "dur": 86.839, + "args": { + "External id": 1420730,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535357410.942, "dur": 2.291, + "args": { + "External id": 1420731,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8634, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535357533.975, "dur": 2149.110, + "args": { + "External id": 1420732,"Sequence number": 15109109, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8635 + } + }, + { + "ph": "f", "id": 410, "pid": 2338710, "tid": 2379450, "ts": 6410535357533.975, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535357665.357, "dur": 124.244, + "args": { + "External id": 1420733,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535357840.998, "dur": 46.197, + "args": { + "External id": 1420734,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535357914.577, "dur": 61.788, + "args": { + "External id": 1420735,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535357988.067, "dur": 38.248, + "args": { + "External id": 1420736,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535358033.834, "dur": 86.556, + "args": { + "External id": 1420737,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535358134.269, "dur": 40.295, + "args": { + "External id": 1420738,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535358186.648, "dur": 34.665, + "args": { + "External id": 1420739,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535358255.307, "dur": 31.049, + "args": { + "External id": 1420740,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535358309.772, "dur": 33.159, + "args": { + "External id": 1420741,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535358368.348, "dur": 22.872, + "args": { + "External id": 1420742,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535358411.843, "dur": 38.639, + "args": { + "External id": 1420743,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535358465.576, "dur": 53.760, + "args": { + "External id": 1420744,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535358524.063, "dur": 43.298, + "args": { + "External id": 1420745,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535358620.710, "dur": 308.933, + "args": { + "External id": 1420746,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535358724.174, "dur": 8.617, + "args": { + "External id": 1420747,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535358735.555, "dur": 3.242, + "args": { + "External id": 1420748,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535358740.089, "dur": 4.627, + "args": { + "External id": 1420749,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535358745.606, "dur": 2.411, + "args": { + "External id": 1420750,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535358806.777, "dur": 7.367, + "args": { + "External id": 1420751,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535358809.256, "dur": 4.673, + "args": { + "External id": 1420752,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535358816.517, "dur": 37.232, + "args": { + "External id": 1420753,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535358822.423, "dur": 2.299, + "args": { + "External id": 1420754,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535358855.784, "dur": 4.806, + "args": { + "External id": 1420755,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535358859.695, "dur": 0.734, + "args": { + "External id": 1420756,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535358861.464, "dur": 18.073, + "args": { + "External id": 1420757,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535358863.807, "dur": 0.482, + "args": { + "External id": 1420758,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535358975.041, "dur": 34.300, + "args": { + "External id": 1420759,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535359028.969, "dur": 20.274, + "args": { + "External id": 1420760,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535359099.478, "dur": 63.025, + "args": { + "External id": 1420761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535359173.309, "dur": 52.682, + "args": { + "External id": 1420762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535359239.945, "dur": 31.086, + "args": { + "External id": 1420763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535359277.691, "dur": 36.462, + "args": { + "External id": 1420764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535359322.917, "dur": 33.626, + "args": { + "External id": 1420765,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535359365.336, "dur": 35.022, + "args": { + "External id": 1420766,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535359445.241, "dur": 32.185, + "args": { + "External id": 1420767,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535359500.644, "dur": 28.378, + "args": { + "External id": 1420768,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535359551.798, "dur": 21.070, + "args": { + "External id": 1420769,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535359591.204, "dur": 18.631, + "args": { + "External id": 1420770,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535359626.376, "dur": 18.708, + "args": { + "External id": 1420771,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359736.957, "dur": 19.280, + "args": { + "External id": 1420772,"Record function id": 0, "Ev Idx": 8675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359741.066, "dur": 13.859, + "args": { + "External id": 1420773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359746.063, "dur": 7.821, + "args": { + "External id": 1420774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359747.878, "dur": 5.852, + "args": { + "External id": 1420775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359761.058, "dur": 5.434, + "args": { + "External id": 1420776,"Record function id": 0, "Ev Idx": 8679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359762.639, "dur": 3.183, + "args": { + "External id": 1420777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359763.347, "dur": 1.832, + "args": { + "External id": 1420778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359764.142, "dur": 0.914, + "args": { + "External id": 1420779,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359770.646, "dur": 4.990, + "args": { + "External id": 1420780,"Record function id": 0, "Ev Idx": 8683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359772.213, "dur": 2.892, + "args": { + "External id": 1420781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359773.079, "dur": 1.505, + "args": { + "External id": 1420782,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359773.716, "dur": 0.742, + "args": { + "External id": 1420783,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359779.565, "dur": 4.414, + "args": { + "External id": 1420784,"Record function id": 0, "Ev Idx": 8687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359780.934, "dur": 2.522, + "args": { + "External id": 1420785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359781.743, "dur": 1.168, + "args": { + "External id": 1420786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359782.096, "dur": 0.737, + "args": { + "External id": 1420787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359787.733, "dur": 14.212, + "args": { + "External id": 1420788,"Record function id": 0, "Ev Idx": 8691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359793.451, "dur": 7.915, + "args": { + "External id": 1420789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359794.375, "dur": 6.320, + "args": { + "External id": 1420790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359797.319, "dur": 3.236, + "args": { + "External id": 1420791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359806.045, "dur": 5.057, + "args": { + "External id": 1420792,"Record function id": 0, "Ev Idx": 8695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359807.575, "dur": 3.026, + "args": { + "External id": 1420793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359808.240, "dur": 1.881, + "args": { + "External id": 1420794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359808.987, "dur": 1.045, + "args": { + "External id": 1420795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359814.974, "dur": 4.705, + "args": { + "External id": 1420796,"Record function id": 0, "Ev Idx": 8699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359816.448, "dur": 2.724, + "args": { + "External id": 1420797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359817.267, "dur": 1.378, + "args": { + "External id": 1420798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359817.732, "dur": 0.823, + "args": { + "External id": 1420799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359823.436, "dur": 38.766, + "args": { + "External id": 1420800,"Record function id": 0, "Ev Idx": 8703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359856.684, "dur": 4.895, + "args": { + "External id": 1420801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359857.424, "dur": 3.578, + "args": { + "External id": 1420802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359860.216, "dur": 0.668, + "args": { + "External id": 1420803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359866.140, "dur": 4.925, + "args": { + "External id": 1420804,"Record function id": 0, "Ev Idx": 8707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535359867.665, "dur": 2.878, + "args": { + "External id": 1420805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359868.229, "dur": 1.634, + "args": { + "External id": 1420806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535359868.900, "dur": 0.856, + "args": { + "External id": 1420807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535359876.193, "dur": 63704.046, + "args": { + "External id": 1420808,"Record function id": 0, "Sequence number": 15109108, "Fwd thread id": 1, "Ev Idx": 8711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535359877.965, "dur": 63692.120, + "args": { + "External id": 1420809,"Sequence number": 15109108, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8712 + } + }, + { + "ph": "f", "id": 411, "pid": 2338710, "tid": 2379450, "ts": 6410535359877.965, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410535359916.769, "dur": 50.982, + "args": { + "External id": 1420810,"Record function id": 0, "Ev Idx": 8713 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410535359977.313, "dur": 76.974, + "args": { + "External id": 1420811,"Record function id": 0, "Ev Idx": 8714 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 2338710, "tid": 2379450, + "ts": 6410535360120.164, "dur": 63439.949, + "args": { + "External id": 1420812,"Record function id": 0, "Ev Idx": 8715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535360241.743, "dur": 9.317, + "args": { + "External id": 1420813,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535360263.869, "dur": 5.836, + "args": { + "External id": 1420814,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535360303.840, "dur": 61995.708, + "args": { + "External id": 1420815,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535360324.016, "dur": 61960.631, + "args": { + "External id": 1420816,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535360458.972, "dur": 24.248, + "args": { + "External id": 1420817,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535360510.739, "dur": 61717.689, + "args": { + "External id": 1420818,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535360514.072, "dur": 61712.829, + "args": { + "External id": 1420819,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535360519.354, "dur": 16.256, + "args": { + "External id": 1420820,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535360537.918, "dur": 61682.849, + "args": { + "External id": 1420821,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535422458.103, "dur": 15.685, + "args": { + "External id": 1420822,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535422462.419, "dur": 10.639, + "args": { + "External id": 1420823,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535422512.919, "dur": 482.274, + "args": { + "External id": 1420824,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535422550.422, "dur": 438.472, + "args": { + "External id": 1420825,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8728, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535422565.524, "dur": 417.078, + "args": { + "External id": 1420826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535423020.651, "dur": 2.918, + "args": { + "External id": 1420827,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8730, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423161.422, "dur": 10.482, + "args": { + "External id": 1420828,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423188.830, "dur": 45.373, + "args": { + "External id": 1420829,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423247.256, "dur": 1.888, + "args": { + "External id": 1420830,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423256.258, "dur": 16.102, + "args": { + "External id": 1420831,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423279.063, "dur": 1.079, + "args": { + "External id": 1420832,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423285.002, "dur": 14.023, + "args": { + "External id": 1420833,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423304.938, "dur": 0.985, + "args": { + "External id": 1420834,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423313.610, "dur": 14.049, + "args": { + "External id": 1420835,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423335.403, "dur": 1.080, + "args": { + "External id": 1420836,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423341.169, "dur": 12.714, + "args": { + "External id": 1420837,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423358.716, "dur": 1.918, + "args": { + "External id": 1420838,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423364.960, "dur": 17.579, + "args": { + "External id": 1420839,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423387.772, "dur": 1.122, + "args": { + "External id": 1420840,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423394.269, "dur": 12.847, + "args": { + "External id": 1420841,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423429.023, "dur": 2.380, + "args": { + "External id": 1420842,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423438.471, "dur": 17.739, + "args": { + "External id": 1420843,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423463.096, "dur": 3.636, + "args": { + "External id": 1420844,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423471.035, "dur": 13.419, + "args": { + "External id": 1420845,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535423599.753, "dur": 3499.194, + "args": { + "External id": 1420846,"Record function id": 0, "Ev Idx": 8749 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410535423624.796, "dur": 1267.112, + "args": { + "External id": 1420847,"Record function id": 0, "Ev Idx": 8750 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410535423644.194, "dur": 381.231, + "args": { + "External id": 1420848,"Record function id": 0, "Ev Idx": 8751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423745.792, "dur": 5.266, + "args": { + "External id": 1420849,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423755.397, "dur": 1.321, + "args": { + "External id": 1420850,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423758.854, "dur": 0.875, + "args": { + "External id": 1420851,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423761.706, "dur": 1.195, + "args": { + "External id": 1420852,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423771.413, "dur": 1.064, + "args": { + "External id": 1420853,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423776.164, "dur": 1.099, + "args": { + "External id": 1420854,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423778.962, "dur": 1.148, + "args": { + "External id": 1420855,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423781.671, "dur": 3.819, + "args": { + "External id": 1420856,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423787.163, "dur": 0.910, + "args": { + "External id": 1420857,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535423791.450, "dur": 1.216, + "args": { + "External id": 1420858,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535423814.204, "dur": 171.928, + "args": { + "External id": 1420859,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535423835.179, "dur": 145.088, + "args": { + "External id": 1420860,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535423851.847, "dur": 16.757, + "args": { + "External id": 1420861,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535423873.306, "dur": 76.618, + "args": { + "External id": 1420862,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535423876.289, "dur": 73.078, + "args": { + "External id": 1420863,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535423880.155, "dur": 6.330, + "args": { + "External id": 1420864,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535423888.155, "dur": 60.362, + "args": { + "External id": 1420865,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8768 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.16", "pid": 2338710, "tid": 2379450, + "ts": 6410535424173.002, "dur": 708.872, + "args": { + "External id": 1420866,"Record function id": 0, "Ev Idx": 8769 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410535424194.778, "dur": 670.880, + "args": { + "External id": 1420867,"Record function id": 0, "Ev Idx": 8770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535424267.029, "dur": 7.512, + "args": { + "External id": 1420868,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535424293.930, "dur": 32.395, + "args": { + "External id": 1420869,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424299.624, "dur": 2.292, + "args": { + "External id": 1420870,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424304.059, "dur": 1.555, + "args": { + "External id": 1420871,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424306.661, "dur": 2.864, + "args": { + "External id": 1420872,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424310.791, "dur": 0.562, + "args": { + "External id": 1420873,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424313.312, "dur": 0.377, + "args": { + "External id": 1420874,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424314.865, "dur": 0.516, + "args": { + "External id": 1420875,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424316.800, "dur": 0.393, + "args": { + "External id": 1420876,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424319.285, "dur": 0.544, + "args": { + "External id": 1420877,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424321.395, "dur": 0.570, + "args": { + "External id": 1420878,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535424339.453, "dur": 50.737, + "args": { + "External id": 1420879,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535424447.991, "dur": 139.853, + "args": { + "External id": 1420880,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535424462.665, "dur": 5.490, + "args": { + "External id": 1420881,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535424475.757, "dur": 17.593, + "args": { + "External id": 1420882,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535424482.796, "dur": 10.022, + "args": { + "External id": 1420883,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424487.654, "dur": 3.018, + "args": { + "External id": 1420884,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535424502.612, "dur": 24.816, + "args": { + "External id": 1420885,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424505.242, "dur": 0.561, + "args": { + "External id": 1420886,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424507.957, "dur": 0.404, + "args": { + "External id": 1420887,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424509.769, "dur": 0.359, + "args": { + "External id": 1420888,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424511.336, "dur": 0.605, + "args": { + "External id": 1420889,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424513.170, "dur": 0.448, + "args": { + "External id": 1420890,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424515.059, "dur": 0.416, + "args": { + "External id": 1420891,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424517.263, "dur": 0.590, + "args": { + "External id": 1420892,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424519.311, "dur": 2.779, + "args": { + "External id": 1420893,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535424523.379, "dur": 0.668, + "args": { + "External id": 1420894,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535424541.732, "dur": 36.947, + "args": { + "External id": 1420895,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535424643.893, "dur": 139.126, + "args": { + "External id": 1420896,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535424677.179, "dur": 101.556, + "args": { + "External id": 1420897,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8800, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535424688.802, "dur": 84.931, + "args": { + "External id": 1420898,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535424803.456, "dur": 2.378, + "args": { + "External id": 1420899,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8802, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535424901.349, "dur": 2129.805, + "args": { + "External id": 1420900,"Sequence number": 15109107, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8803 + } + }, + { + "ph": "f", "id": 412, "pid": 2338710, "tid": 2379450, "ts": 6410535424901.349, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535425037.860, "dur": 169.142, + "args": { + "External id": 1420901,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535425264.460, "dur": 49.742, + "args": { + "External id": 1420902,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535425339.522, "dur": 62.543, + "args": { + "External id": 1420903,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535425431.083, "dur": 46.566, + "args": { + "External id": 1420904,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535425488.292, "dur": 39.262, + "args": { + "External id": 1420905,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535425535.567, "dur": 32.438, + "args": { + "External id": 1420906,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535425579.180, "dur": 34.347, + "args": { + "External id": 1420907,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535425643.703, "dur": 29.164, + "args": { + "External id": 1420908,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535425697.698, "dur": 34.608, + "args": { + "External id": 1420909,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535425757.880, "dur": 26.149, + "args": { + "External id": 1420910,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535425802.508, "dur": 19.924, + "args": { + "External id": 1420911,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535425835.884, "dur": 62.032, + "args": { + "External id": 1420912,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535425908.748, "dur": 49.107, + "args": { + "External id": 1420913,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535425998.134, "dur": 349.414, + "args": { + "External id": 1420914,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535426141.955, "dur": 8.291, + "args": { + "External id": 1420915,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535426153.006, "dur": 3.910, + "args": { + "External id": 1420916,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535426158.351, "dur": 5.572, + "args": { + "External id": 1420917,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535426165.615, "dur": 2.886, + "args": { + "External id": 1420918,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535426223.528, "dur": 6.007, + "args": { + "External id": 1420919,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535426225.893, "dur": 3.418, + "args": { + "External id": 1420920,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535426231.684, "dur": 39.380, + "args": { + "External id": 1420921,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535426238.195, "dur": 2.257, + "args": { + "External id": 1420922,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535426273.184, "dur": 2.090, + "args": { + "External id": 1420923,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535426274.309, "dur": 0.849, + "args": { + "External id": 1420924,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535426276.634, "dur": 17.927, + "args": { + "External id": 1420925,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535426278.923, "dur": 0.721, + "args": { + "External id": 1420926,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535426392.665, "dur": 54.781, + "args": { + "External id": 1420927,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535426473.406, "dur": 21.180, + "args": { + "External id": 1420928,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535426506.573, "dur": 56.400, + "args": { + "External id": 1420929,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535426572.293, "dur": 46.342, + "args": { + "External id": 1420930,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535426630.926, "dur": 26.316, + "args": { + "External id": 1420931,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535426665.073, "dur": 36.263, + "args": { + "External id": 1420932,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535426710.183, "dur": 32.577, + "args": { + "External id": 1420933,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535426751.200, "dur": 35.037, + "args": { + "External id": 1420934,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535426808.695, "dur": 28.810, + "args": { + "External id": 1420935,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535426856.695, "dur": 29.044, + "args": { + "External id": 1420936,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535426902.370, "dur": 21.260, + "args": { + "External id": 1420937,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535426939.197, "dur": 16.630, + "args": { + "External id": 1420938,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535426971.049, "dur": 18.383, + "args": { + "External id": 1420939,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427127.299, "dur": 34.897, + "args": { + "External id": 1420940,"Record function id": 0, "Ev Idx": 8843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427132.325, "dur": 28.582, + "args": { + "External id": 1420941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427151.656, "dur": 7.364, + "args": { + "External id": 1420942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427154.028, "dur": 4.815, + "args": { + "External id": 1420943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427167.266, "dur": 6.700, + "args": { + "External id": 1420944,"Record function id": 0, "Ev Idx": 8847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427169.271, "dur": 4.142, + "args": { + "External id": 1420945,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427170.402, "dur": 2.363, + "args": { + "External id": 1420946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427171.423, "dur": 1.225, + "args": { + "External id": 1420947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427177.955, "dur": 5.803, + "args": { + "External id": 1420948,"Record function id": 0, "Ev Idx": 8851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427179.639, "dur": 3.613, + "args": { + "External id": 1420949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427180.346, "dur": 2.305, + "args": { + "External id": 1420950,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427180.994, "dur": 1.515, + "args": { + "External id": 1420951,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427187.638, "dur": 4.613, + "args": { + "External id": 1420952,"Record function id": 0, "Ev Idx": 8855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427189.031, "dur": 2.705, + "args": { + "External id": 1420953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427189.681, "dur": 1.576, + "args": { + "External id": 1420954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427190.394, "dur": 0.766, + "args": { + "External id": 1420955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427196.213, "dur": 7.760, + "args": { + "External id": 1420956,"Record function id": 0, "Ev Idx": 8859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427197.595, "dur": 5.901, + "args": { + "External id": 1420957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427198.688, "dur": 4.180, + "args": { + "External id": 1420958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427199.266, "dur": 3.466, + "args": { + "External id": 1420959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427207.810, "dur": 5.546, + "args": { + "External id": 1420960,"Record function id": 0, "Ev Idx": 8863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427209.588, "dur": 3.229, + "args": { + "External id": 1420961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427210.164, "dur": 1.901, + "args": { + "External id": 1420962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427210.829, "dur": 1.129, + "args": { + "External id": 1420963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427217.305, "dur": 4.220, + "args": { + "External id": 1420964,"Record function id": 0, "Ev Idx": 8867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427218.644, "dur": 2.348, + "args": { + "External id": 1420965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427219.233, "dur": 1.160, + "args": { + "External id": 1420966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427219.584, "dur": 0.713, + "args": { + "External id": 1420967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427225.911, "dur": 7.529, + "args": { + "External id": 1420968,"Record function id": 0, "Ev Idx": 8871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427227.277, "dur": 5.644, + "args": { + "External id": 1420969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427228.291, "dur": 3.960, + "args": { + "External id": 1420970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427231.040, "dur": 1.030, + "args": { + "External id": 1420971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427237.783, "dur": 5.018, + "args": { + "External id": 1420972,"Record function id": 0, "Ev Idx": 8875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535427239.104, "dur": 3.176, + "args": { + "External id": 1420973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427239.744, "dur": 1.679, + "args": { + "External id": 1420974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535427240.430, "dur": 0.902, + "args": { + "External id": 1420975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535427247.514, "dur": 61753.206, + "args": { + "External id": 1420976,"Record function id": 0, "Sequence number": 15109106, "Fwd thread id": 1, "Ev Idx": 8879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535427249.030, "dur": 61739.368, + "args": { + "External id": 1420977,"Sequence number": 15109106, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8880 + } + }, + { + "ph": "f", "id": 413, "pid": 2338710, "tid": 2379450, "ts": 6410535427249.030, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410535427284.667, "dur": 48.716, + "args": { + "External id": 1420978,"Record function id": 0, "Ev Idx": 8881 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410535427342.853, "dur": 97.297, + "args": { + "External id": 1420979,"Record function id": 0, "Ev Idx": 8882 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 2338710, "tid": 2379450, + "ts": 6410535427449.618, "dur": 61529.107, + "args": { + "External id": 1420980,"Record function id": 0, "Ev Idx": 8883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535427560.185, "dur": 17.481, + "args": { + "External id": 1420981,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535427600.142, "dur": 6.666, + "args": { + "External id": 1420982,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535427627.891, "dur": 60215.356, + "args": { + "External id": 1420983,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535427648.891, "dur": 60179.089, + "args": { + "External id": 1420984,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535427757.022, "dur": 21.644, + "args": { + "External id": 1420985,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535427802.758, "dur": 59972.682, + "args": { + "External id": 1420986,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535427805.775, "dur": 59968.303, + "args": { + "External id": 1420987,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535427819.765, "dur": 11.212, + "args": { + "External id": 1420988,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535427834.374, "dur": 59934.739, + "args": { + "External id": 1420989,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535487969.800, "dur": 15.442, + "args": { + "External id": 1420990,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535487974.299, "dur": 10.517, + "args": { + "External id": 1420991,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488023.555, "dur": 494.157, + "args": { + "External id": 1420992,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535488093.141, "dur": 417.986, + "args": { + "External id": 1420993,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8896, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535488111.469, "dur": 392.673, + "args": { + "External id": 1420994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535488544.363, "dur": 2.937, + "args": { + "External id": 1420995,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8898, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488622.336, "dur": 10.580, + "args": { + "External id": 1420996,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488649.666, "dur": 41.767, + "args": { + "External id": 1420997,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488703.986, "dur": 2.052, + "args": { + "External id": 1420998,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488712.069, "dur": 16.885, + "args": { + "External id": 1420999,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488735.349, "dur": 0.995, + "args": { + "External id": 1421000,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488742.010, "dur": 13.394, + "args": { + "External id": 1421001,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488761.024, "dur": 1.000, + "args": { + "External id": 1421002,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488767.284, "dur": 15.100, + "args": { + "External id": 1421003,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488787.476, "dur": 1.384, + "args": { + "External id": 1421004,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488794.071, "dur": 12.727, + "args": { + "External id": 1421005,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488811.979, "dur": 1.458, + "args": { + "External id": 1421006,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488818.371, "dur": 13.562, + "args": { + "External id": 1421007,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488837.276, "dur": 1.048, + "args": { + "External id": 1421008,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488842.622, "dur": 12.562, + "args": { + "External id": 1421009,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488862.365, "dur": 0.990, + "args": { + "External id": 1421010,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488868.466, "dur": 13.569, + "args": { + "External id": 1421011,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535488886.510, "dur": 3.672, + "args": { + "External id": 1421012,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535488894.756, "dur": 13.477, + "args": { + "External id": 1421013,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535489018.136, "dur": 3566.818, + "args": { + "External id": 1421014,"Record function id": 0, "Ev Idx": 8917 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410535489040.502, "dur": 1340.092, + "args": { + "External id": 1421015,"Record function id": 0, "Ev Idx": 8918 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410535489103.891, "dur": 418.933, + "args": { + "External id": 1421016,"Record function id": 0, "Ev Idx": 8919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489220.597, "dur": 5.769, + "args": { + "External id": 1421017,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489230.376, "dur": 0.822, + "args": { + "External id": 1421018,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489233.661, "dur": 0.921, + "args": { + "External id": 1421019,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489236.770, "dur": 0.991, + "args": { + "External id": 1421020,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489239.540, "dur": 1.198, + "args": { + "External id": 1421021,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489245.834, "dur": 1.119, + "args": { + "External id": 1421022,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489249.030, "dur": 0.886, + "args": { + "External id": 1421023,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489251.672, "dur": 4.493, + "args": { + "External id": 1421024,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489257.803, "dur": 0.902, + "args": { + "External id": 1421025,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535489262.455, "dur": 0.692, + "args": { + "External id": 1421026,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535489284.746, "dur": 196.593, + "args": { + "External id": 1421027,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535489304.722, "dur": 170.428, + "args": { + "External id": 1421028,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535489323.891, "dur": 18.435, + "args": { + "External id": 1421029,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535489347.025, "dur": 95.042, + "args": { + "External id": 1421030,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535489350.477, "dur": 91.060, + "args": { + "External id": 1421031,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489355.526, "dur": 6.287, + "args": { + "External id": 1421032,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535489363.968, "dur": 76.277, + "args": { + "External id": 1421033,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8936 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.15", "pid": 2338710, "tid": 2379450, + "ts": 6410535489627.771, "dur": 742.753, + "args": { + "External id": 1421034,"Record function id": 0, "Ev Idx": 8937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410535489649.594, "dur": 705.247, + "args": { + "External id": 1421035,"Record function id": 0, "Ev Idx": 8938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535489726.406, "dur": 6.513, + "args": { + "External id": 1421036,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535489751.670, "dur": 34.463, + "args": { + "External id": 1421037,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489757.867, "dur": 1.829, + "args": { + "External id": 1421038,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489762.877, "dur": 0.457, + "args": { + "External id": 1421039,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489764.749, "dur": 3.307, + "args": { + "External id": 1421040,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489770.031, "dur": 0.553, + "args": { + "External id": 1421041,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489772.839, "dur": 0.540, + "args": { + "External id": 1421042,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489774.726, "dur": 0.624, + "args": { + "External id": 1421043,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489777.593, "dur": 0.473, + "args": { + "External id": 1421044,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489779.717, "dur": 0.443, + "args": { + "External id": 1421045,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489781.453, "dur": 0.554, + "args": { + "External id": 1421046,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535489799.664, "dur": 51.957, + "args": { + "External id": 1421047,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535489891.512, "dur": 128.528, + "args": { + "External id": 1421048,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535489904.413, "dur": 3.757, + "args": { + "External id": 1421049,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535489914.814, "dur": 14.654, + "args": { + "External id": 1421050,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535489919.900, "dur": 9.070, + "args": { + "External id": 1421051,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489924.622, "dur": 2.780, + "args": { + "External id": 1421052,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535489937.585, "dur": 28.603, + "args": { + "External id": 1421053,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489940.196, "dur": 0.964, + "args": { + "External id": 1421054,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489943.183, "dur": 0.566, + "args": { + "External id": 1421055,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489945.778, "dur": 0.400, + "args": { + "External id": 1421056,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489947.509, "dur": 0.682, + "args": { + "External id": 1421057,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489950.283, "dur": 0.539, + "args": { + "External id": 1421058,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489952.566, "dur": 0.380, + "args": { + "External id": 1421059,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489954.386, "dur": 0.652, + "args": { + "External id": 1421060,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489957.089, "dur": 2.737, + "args": { + "External id": 1421061,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535489961.723, "dur": 0.557, + "args": { + "External id": 1421062,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535489980.048, "dur": 31.651, + "args": { + "External id": 1421063,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535490117.225, "dur": 149.178, + "args": { + "External id": 1421064,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535490150.510, "dur": 111.431, + "args": { + "External id": 1421065,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8968, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535490166.253, "dur": 90.494, + "args": { + "External id": 1421066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535490287.347, "dur": 2.349, + "args": { + "External id": 1421067,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8970, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535490389.430, "dur": 2168.519, + "args": { + "External id": 1421068,"Sequence number": 15109105, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8971 + } + }, + { + "ph": "f", "id": 414, "pid": 2338710, "tid": 2379450, "ts": 6410535490389.430, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535490546.709, "dur": 126.243, + "args": { + "External id": 1421069,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535490724.028, "dur": 50.356, + "args": { + "External id": 1421070,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535490798.043, "dur": 60.878, + "args": { + "External id": 1421071,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535490870.822, "dur": 36.475, + "args": { + "External id": 1421072,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535490914.713, "dur": 36.814, + "args": { + "External id": 1421073,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535490959.350, "dur": 31.939, + "args": { + "External id": 1421074,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535491002.077, "dur": 33.412, + "args": { + "External id": 1421075,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535491110.012, "dur": 32.666, + "args": { + "External id": 1421076,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535491168.645, "dur": 33.563, + "args": { + "External id": 1421077,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535491230.349, "dur": 23.275, + "args": { + "External id": 1421078,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535491277.577, "dur": 16.803, + "args": { + "External id": 1421079,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535491307.432, "dur": 52.752, + "args": { + "External id": 1421080,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535491365.286, "dur": 38.101, + "args": { + "External id": 1421081,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535491456.845, "dur": 330.296, + "args": { + "External id": 1421082,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535491577.132, "dur": 13.584, + "args": { + "External id": 1421083,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535491594.232, "dur": 4.032, + "args": { + "External id": 1421084,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535491599.926, "dur": 4.537, + "args": { + "External id": 1421085,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535491606.010, "dur": 2.500, + "args": { + "External id": 1421086,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535491667.110, "dur": 6.340, + "args": { + "External id": 1421087,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535491669.816, "dur": 3.424, + "args": { + "External id": 1421088,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535491675.915, "dur": 37.581, + "args": { + "External id": 1421089,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535491682.888, "dur": 2.230, + "args": { + "External id": 1421090,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535491715.339, "dur": 2.433, + "args": { + "External id": 1421091,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535491716.692, "dur": 0.945, + "args": { + "External id": 1421092,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535491719.231, "dur": 17.111, + "args": { + "External id": 1421093,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535491721.562, "dur": 0.747, + "args": { + "External id": 1421094,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535491835.070, "dur": 37.524, + "args": { + "External id": 1421095,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535491893.240, "dur": 19.608, + "args": { + "External id": 1421096,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535491926.844, "dur": 57.359, + "args": { + "External id": 1421097,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535491993.533, "dur": 46.104, + "args": { + "External id": 1421098,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535492094.193, "dur": 34.938, + "args": { + "External id": 1421099,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535492140.743, "dur": 38.236, + "args": { + "External id": 1421100,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535492188.877, "dur": 33.134, + "args": { + "External id": 1421101,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535492231.424, "dur": 36.673, + "args": { + "External id": 1421102,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535492293.223, "dur": 29.607, + "args": { + "External id": 1421103,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535492342.015, "dur": 29.413, + "args": { + "External id": 1421104,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535492400.072, "dur": 37.387, + "args": { + "External id": 1421105,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535492462.461, "dur": 18.604, + "args": { + "External id": 1421106,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535492498.883, "dur": 19.494, + "args": { + "External id": 1421107,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492611.423, "dur": 18.612, + "args": { + "External id": 1421108,"Record function id": 0, "Ev Idx": 9011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492615.440, "dur": 13.552, + "args": { + "External id": 1421109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492620.562, "dur": 7.140, + "args": { + "External id": 1421110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492622.612, "dur": 4.880, + "args": { + "External id": 1421111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492635.037, "dur": 6.249, + "args": { + "External id": 1421112,"Record function id": 0, "Ev Idx": 9015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492636.763, "dur": 3.955, + "args": { + "External id": 1421113,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492637.612, "dur": 2.487, + "args": { + "External id": 1421114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492638.752, "dur": 1.173, + "args": { + "External id": 1421115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492645.346, "dur": 5.204, + "args": { + "External id": 1421116,"Record function id": 0, "Ev Idx": 9019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492646.901, "dur": 3.133, + "args": { + "External id": 1421117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492647.602, "dur": 1.796, + "args": { + "External id": 1421118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492648.165, "dur": 1.143, + "args": { + "External id": 1421119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492654.451, "dur": 4.389, + "args": { + "External id": 1421120,"Record function id": 0, "Ev Idx": 9023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492655.800, "dur": 2.541, + "args": { + "External id": 1421121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492656.410, "dur": 1.401, + "args": { + "External id": 1421122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492656.930, "dur": 0.791, + "args": { + "External id": 1421123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492662.632, "dur": 7.670, + "args": { + "External id": 1421124,"Record function id": 0, "Ev Idx": 9027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492664.145, "dur": 5.665, + "args": { + "External id": 1421125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492665.126, "dur": 4.139, + "args": { + "External id": 1421126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492665.714, "dur": 3.463, + "args": { + "External id": 1421127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492674.410, "dur": 5.558, + "args": { + "External id": 1421128,"Record function id": 0, "Ev Idx": 9031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492676.049, "dur": 3.388, + "args": { + "External id": 1421129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492677.023, "dur": 1.899, + "args": { + "External id": 1421130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492677.738, "dur": 1.068, + "args": { + "External id": 1421131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492683.930, "dur": 4.456, + "args": { + "External id": 1421132,"Record function id": 0, "Ev Idx": 9035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492685.274, "dur": 2.599, + "args": { + "External id": 1421133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492686.072, "dur": 1.273, + "args": { + "External id": 1421134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492686.591, "dur": 0.666, + "args": { + "External id": 1421135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492692.225, "dur": 4.522, + "args": { + "External id": 1421136,"Record function id": 0, "Ev Idx": 9039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492693.381, "dur": 2.834, + "args": { + "External id": 1421137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492693.994, "dur": 1.519, + "args": { + "External id": 1421138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492694.545, "dur": 0.841, + "args": { + "External id": 1421139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492701.417, "dur": 5.119, + "args": { + "External id": 1421140,"Record function id": 0, "Ev Idx": 9043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535492702.832, "dur": 3.201, + "args": { + "External id": 1421141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492703.577, "dur": 1.952, + "args": { + "External id": 1421142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535492704.623, "dur": 0.762, + "args": { + "External id": 1421143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535492711.438, "dur": 62048.915, + "args": { + "External id": 1421144,"Record function id": 0, "Sequence number": 15109104, "Fwd thread id": 1, "Ev Idx": 9047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535492712.952, "dur": 62036.388, + "args": { + "External id": 1421145,"Sequence number": 15109104, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9048 + } + }, + { + "ph": "f", "id": 415, "pid": 2338710, "tid": 2379450, "ts": 6410535492712.952, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410535492746.684, "dur": 44.493, + "args": { + "External id": 1421146,"Record function id": 0, "Ev Idx": 9049 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410535492800.303, "dur": 75.602, + "args": { + "External id": 1421147,"Record function id": 0, "Ev Idx": 9050 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 2338710, "tid": 2379450, + "ts": 6410535492882.975, "dur": 61857.133, + "args": { + "External id": 1421148,"Record function id": 0, "Ev Idx": 9051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535492991.839, "dur": 7.838, + "args": { + "External id": 1421149,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535493011.416, "dur": 5.504, + "args": { + "External id": 1421150,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535493033.972, "dur": 60566.238, + "args": { + "External id": 1421151,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535493050.634, "dur": 60533.711, + "args": { + "External id": 1421152,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535493219.762, "dur": 25.617, + "args": { + "External id": 1421153,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535493273.919, "dur": 60262.029, + "args": { + "External id": 1421154,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535493279.782, "dur": 60255.024, + "args": { + "External id": 1421155,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535493284.877, "dur": 14.259, + "args": { + "External id": 1421156,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535493301.413, "dur": 60229.219, + "args": { + "External id": 1421157,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535553723.877, "dur": 13.710, + "args": { + "External id": 1421158,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535553728.008, "dur": 9.130, + "args": { + "External id": 1421159,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535553776.269, "dur": 477.816, + "args": { + "External id": 1421160,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535553814.160, "dur": 433.179, + "args": { + "External id": 1421161,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9064, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535553828.388, "dur": 411.395, + "args": { + "External id": 1421162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535554280.990, "dur": 2.982, + "args": { + "External id": 1421163,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9066, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554359.234, "dur": 9.715, + "args": { + "External id": 1421164,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554384.833, "dur": 59.419, + "args": { + "External id": 1421165,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554460.770, "dur": 3.042, + "args": { + "External id": 1421166,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554470.820, "dur": 17.940, + "args": { + "External id": 1421167,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554495.339, "dur": 1.000, + "args": { + "External id": 1421168,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554501.326, "dur": 14.020, + "args": { + "External id": 1421169,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554521.606, "dur": 0.957, + "args": { + "External id": 1421170,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554527.775, "dur": 13.956, + "args": { + "External id": 1421171,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554547.139, "dur": 1.095, + "args": { + "External id": 1421172,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554552.952, "dur": 13.206, + "args": { + "External id": 1421173,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554570.973, "dur": 1.144, + "args": { + "External id": 1421174,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554576.733, "dur": 13.258, + "args": { + "External id": 1421175,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554595.179, "dur": 0.857, + "args": { + "External id": 1421176,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554600.599, "dur": 12.605, + "args": { + "External id": 1421177,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554617.712, "dur": 0.971, + "args": { + "External id": 1421178,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554623.411, "dur": 14.515, + "args": { + "External id": 1421179,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535554645.441, "dur": 3.318, + "args": { + "External id": 1421180,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535554653.663, "dur": 14.203, + "args": { + "External id": 1421181,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535554778.781, "dur": 3577.868, + "args": { + "External id": 1421182,"Record function id": 0, "Ev Idx": 9085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410535554801.719, "dur": 1363.786, + "args": { + "External id": 1421183,"Record function id": 0, "Ev Idx": 9086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410535554818.438, "dur": 446.252, + "args": { + "External id": 1421184,"Record function id": 0, "Ev Idx": 9087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554919.247, "dur": 4.794, + "args": { + "External id": 1421185,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554927.699, "dur": 1.372, + "args": { + "External id": 1421186,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554932.055, "dur": 1.344, + "args": { + "External id": 1421187,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554935.670, "dur": 0.990, + "args": { + "External id": 1421188,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554938.967, "dur": 1.069, + "args": { + "External id": 1421189,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554941.812, "dur": 0.936, + "args": { + "External id": 1421190,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554944.603, "dur": 1.066, + "args": { + "External id": 1421191,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554949.933, "dur": 4.127, + "args": { + "External id": 1421192,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554955.800, "dur": 1.083, + "args": { + "External id": 1421193,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535554958.454, "dur": 0.859, + "args": { + "External id": 1421194,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535554981.178, "dur": 240.121, + "args": { + "External id": 1421195,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535555001.834, "dur": 212.090, + "args": { + "External id": 1421196,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535555019.463, "dur": 17.825, + "args": { + "External id": 1421197,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535555042.320, "dur": 138.773, + "args": { + "External id": 1421198,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535555045.699, "dur": 134.762, + "args": { + "External id": 1421199,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555050.661, "dur": 64.580, + "args": { + "External id": 1421200,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535555118.595, "dur": 61.230, + "args": { + "External id": 1421201,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.14", "pid": 2338710, "tid": 2379450, + "ts": 6410535555372.587, "dur": 783.300, + "args": { + "External id": 1421202,"Record function id": 0, "Ev Idx": 9105 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410535555398.204, "dur": 740.674, + "args": { + "External id": 1421203,"Record function id": 0, "Ev Idx": 9106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535555502.695, "dur": 7.797, + "args": { + "External id": 1421204,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535555528.698, "dur": 37.472, + "args": { + "External id": 1421205,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555535.037, "dur": 2.448, + "args": { + "External id": 1421206,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555540.271, "dur": 0.595, + "args": { + "External id": 1421207,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555542.946, "dur": 2.790, + "args": { + "External id": 1421208,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555547.420, "dur": 0.576, + "args": { + "External id": 1421209,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555552.897, "dur": 0.370, + "args": { + "External id": 1421210,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555554.986, "dur": 0.328, + "args": { + "External id": 1421211,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555556.724, "dur": 0.404, + "args": { + "External id": 1421212,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555558.926, "dur": 0.489, + "args": { + "External id": 1421213,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555561.383, "dur": 0.408, + "args": { + "External id": 1421214,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535555579.416, "dur": 55.263, + "args": { + "External id": 1421215,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535555672.471, "dur": 139.254, + "args": { + "External id": 1421216,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535555686.063, "dur": 4.142, + "args": { + "External id": 1421217,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535555696.843, "dur": 14.672, + "args": { + "External id": 1421218,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535555702.046, "dur": 8.955, + "args": { + "External id": 1421219,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555706.495, "dur": 2.974, + "args": { + "External id": 1421220,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535555719.980, "dur": 35.613, + "args": { + "External id": 1421221,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555726.201, "dur": 5.334, + "args": { + "External id": 1421222,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555733.509, "dur": 0.507, + "args": { + "External id": 1421223,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555736.032, "dur": 0.403, + "args": { + "External id": 1421224,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555737.961, "dur": 0.410, + "args": { + "External id": 1421225,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555740.248, "dur": 0.452, + "args": { + "External id": 1421226,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555742.237, "dur": 0.583, + "args": { + "External id": 1421227,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555744.416, "dur": 0.321, + "args": { + "External id": 1421228,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555746.959, "dur": 2.734, + "args": { + "External id": 1421229,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535555751.607, "dur": 0.401, + "args": { + "External id": 1421230,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535555768.063, "dur": 34.240, + "args": { + "External id": 1421231,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535555868.982, "dur": 138.799, + "args": { + "External id": 1421232,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535555900.109, "dur": 103.548, + "args": { + "External id": 1421233,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9136, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535555911.783, "dur": 86.768, + "args": { + "External id": 1421234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535556028.462, "dur": 2.333, + "args": { + "External id": 1421235,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9138, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535556176.155, "dur": 2153.992, + "args": { + "External id": 1421236,"Sequence number": 15109103, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9139 + } + }, + { + "ph": "f", "id": 416, "pid": 2338710, "tid": 2379450, "ts": 6410535556176.155, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535556312.929, "dur": 147.046, + "args": { + "External id": 1421237,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535556515.356, "dur": 47.346, + "args": { + "External id": 1421238,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535556586.173, "dur": 63.522, + "args": { + "External id": 1421239,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535556661.604, "dur": 36.615, + "args": { + "External id": 1421240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535556705.658, "dur": 36.393, + "args": { + "External id": 1421241,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535556749.499, "dur": 32.620, + "args": { + "External id": 1421242,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535556792.664, "dur": 32.893, + "args": { + "External id": 1421243,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535556855.855, "dur": 27.111, + "args": { + "External id": 1421244,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535556907.977, "dur": 36.108, + "args": { + "External id": 1421245,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535556969.036, "dur": 26.074, + "args": { + "External id": 1421246,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535557012.257, "dur": 15.774, + "args": { + "External id": 1421247,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535557041.516, "dur": 90.936, + "args": { + "External id": 1421248,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535557140.192, "dur": 59.354, + "args": { + "External id": 1421249,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535557246.766, "dur": 331.900, + "args": { + "External id": 1421250,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535557352.943, "dur": 7.872, + "args": { + "External id": 1421251,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535557363.773, "dur": 3.099, + "args": { + "External id": 1421252,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535557368.655, "dur": 5.043, + "args": { + "External id": 1421253,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535557375.623, "dur": 2.437, + "args": { + "External id": 1421254,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535557449.518, "dur": 6.363, + "args": { + "External id": 1421255,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535557451.869, "dur": 3.597, + "args": { + "External id": 1421256,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535557457.839, "dur": 39.873, + "args": { + "External id": 1421257,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535557464.712, "dur": 2.083, + "args": { + "External id": 1421258,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535557499.530, "dur": 2.561, + "args": { + "External id": 1421259,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535557501.250, "dur": 0.759, + "args": { + "External id": 1421260,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535557503.682, "dur": 18.767, + "args": { + "External id": 1421261,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535557505.954, "dur": 0.639, + "args": { + "External id": 1421262,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535557632.959, "dur": 36.163, + "args": { + "External id": 1421263,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535557689.473, "dur": 21.053, + "args": { + "External id": 1421264,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535557720.994, "dur": 57.919, + "args": { + "External id": 1421265,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535557788.017, "dur": 48.380, + "args": { + "External id": 1421266,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535557848.778, "dur": 27.219, + "args": { + "External id": 1421267,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535557883.399, "dur": 37.707, + "args": { + "External id": 1421268,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535557929.768, "dur": 33.210, + "args": { + "External id": 1421269,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535557983.593, "dur": 36.876, + "args": { + "External id": 1421270,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535558044.609, "dur": 71.152, + "args": { + "External id": 1421271,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535558140.953, "dur": 32.111, + "args": { + "External id": 1421272,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535558193.404, "dur": 21.680, + "args": { + "External id": 1421273,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535558236.326, "dur": 17.420, + "args": { + "External id": 1421274,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535558273.962, "dur": 19.301, + "args": { + "External id": 1421275,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558383.022, "dur": 18.356, + "args": { + "External id": 1421276,"Record function id": 0, "Ev Idx": 9179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558386.827, "dur": 13.179, + "args": { + "External id": 1421277,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558392.149, "dur": 6.718, + "args": { + "External id": 1421278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558394.408, "dur": 4.319, + "args": { + "External id": 1421279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558406.087, "dur": 6.445, + "args": { + "External id": 1421280,"Record function id": 0, "Ev Idx": 9183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558407.442, "dur": 4.534, + "args": { + "External id": 1421281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558408.521, "dur": 2.771, + "args": { + "External id": 1421282,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558409.676, "dur": 1.480, + "args": { + "External id": 1421283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558436.521, "dur": 8.641, + "args": { + "External id": 1421284,"Record function id": 0, "Ev Idx": 9187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558438.507, "dur": 5.701, + "args": { + "External id": 1421285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558440.197, "dur": 2.782, + "args": { + "External id": 1421286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558440.869, "dur": 1.858, + "args": { + "External id": 1421287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558449.433, "dur": 7.212, + "args": { + "External id": 1421288,"Record function id": 0, "Ev Idx": 9191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558450.833, "dur": 5.299, + "args": { + "External id": 1421289,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558451.914, "dur": 3.729, + "args": { + "External id": 1421290,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558452.434, "dur": 3.120, + "args": { + "External id": 1421291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558460.413, "dur": 5.008, + "args": { + "External id": 1421292,"Record function id": 0, "Ev Idx": 9195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558462.136, "dur": 2.763, + "args": { + "External id": 1421293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558462.781, "dur": 1.646, + "args": { + "External id": 1421294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558463.260, "dur": 1.073, + "args": { + "External id": 1421295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558469.301, "dur": 5.346, + "args": { + "External id": 1421296,"Record function id": 0, "Ev Idx": 9199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558470.839, "dur": 3.255, + "args": { + "External id": 1421297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558471.639, "dur": 1.714, + "args": { + "External id": 1421298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558472.401, "dur": 0.840, + "args": { + "External id": 1421299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558478.496, "dur": 4.579, + "args": { + "External id": 1421300,"Record function id": 0, "Ev Idx": 9203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558479.747, "dur": 2.793, + "args": { + "External id": 1421301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558480.567, "dur": 1.333, + "args": { + "External id": 1421302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558480.967, "dur": 0.841, + "args": { + "External id": 1421303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558487.611, "dur": 4.168, + "args": { + "External id": 1421304,"Record function id": 0, "Ev Idx": 9207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558488.902, "dur": 2.339, + "args": { + "External id": 1421305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558489.579, "dur": 1.175, + "args": { + "External id": 1421306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558489.930, "dur": 0.704, + "args": { + "External id": 1421307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558496.151, "dur": 4.450, + "args": { + "External id": 1421308,"Record function id": 0, "Ev Idx": 9211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535558497.331, "dur": 2.757, + "args": { + "External id": 1421309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558497.910, "dur": 1.665, + "args": { + "External id": 1421310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535558498.633, "dur": 0.794, + "args": { + "External id": 1421311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535558505.696, "dur": 61044.346, + "args": { + "External id": 1421312,"Record function id": 0, "Sequence number": 15109102, "Fwd thread id": 1, "Ev Idx": 9215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535558543.320, "dur": 60994.158, + "args": { + "External id": 1421313,"Sequence number": 15109102, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9216 + } + }, + { + "ph": "f", "id": 417, "pid": 2338710, "tid": 2379450, "ts": 6410535558543.320, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410535558590.021, "dur": 46.653, + "args": { + "External id": 1421314,"Record function id": 0, "Ev Idx": 9217 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410535558646.579, "dur": 75.335, + "args": { + "External id": 1421315,"Record function id": 0, "Ev Idx": 9218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 2338710, "tid": 2379450, + "ts": 6410535558728.734, "dur": 60798.875, + "args": { + "External id": 1421316,"Record function id": 0, "Ev Idx": 9219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535558857.461, "dur": 11.693, + "args": { + "External id": 1421317,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535558885.137, "dur": 5.804, + "args": { + "External id": 1421318,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535558908.646, "dur": 59403.363, + "args": { + "External id": 1421319,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535558927.940, "dur": 59368.582, + "args": { + "External id": 1421320,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535559043.825, "dur": 67.830, + "args": { + "External id": 1421321,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535559139.660, "dur": 59102.015, + "args": { + "External id": 1421322,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535559143.463, "dur": 59096.979, + "args": { + "External id": 1421323,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535559150.328, "dur": 16.922, + "args": { + "External id": 1421324,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535559170.473, "dur": 59064.420, + "args": { + "External id": 1421325,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535618452.249, "dur": 14.889, + "args": { + "External id": 1421326,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535618456.142, "dur": 10.325, + "args": { + "External id": 1421327,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535618504.263, "dur": 482.939, + "args": { + "External id": 1421328,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535618539.019, "dur": 441.906, + "args": { + "External id": 1421329,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9232, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535618553.908, "dur": 420.682, + "args": { + "External id": 1421330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535619009.416, "dur": 2.687, + "args": { + "External id": 1421331,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9234, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619142.542, "dur": 8.904, + "args": { + "External id": 1421332,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619167.413, "dur": 46.657, + "args": { + "External id": 1421333,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619225.902, "dur": 2.301, + "args": { + "External id": 1421334,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619234.828, "dur": 16.820, + "args": { + "External id": 1421335,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619258.613, "dur": 1.165, + "args": { + "External id": 1421336,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619265.049, "dur": 12.464, + "args": { + "External id": 1421337,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619283.549, "dur": 1.239, + "args": { + "External id": 1421338,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619289.789, "dur": 14.524, + "args": { + "External id": 1421339,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619309.471, "dur": 1.142, + "args": { + "External id": 1421340,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619315.116, "dur": 12.304, + "args": { + "External id": 1421341,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619332.639, "dur": 1.212, + "args": { + "External id": 1421342,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619338.670, "dur": 13.823, + "args": { + "External id": 1421343,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619357.429, "dur": 3.657, + "args": { + "External id": 1421344,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619365.827, "dur": 13.009, + "args": { + "External id": 1421345,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619384.462, "dur": 1.150, + "args": { + "External id": 1421346,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619390.322, "dur": 13.898, + "args": { + "External id": 1421347,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619409.489, "dur": 1.166, + "args": { + "External id": 1421348,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619431.531, "dur": 17.310, + "args": { + "External id": 1421349,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535619568.885, "dur": 3568.113, + "args": { + "External id": 1421350,"Record function id": 0, "Ev Idx": 9253 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410535619592.113, "dur": 1253.790, + "args": { + "External id": 1421351,"Record function id": 0, "Ev Idx": 9254 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410535619609.730, "dur": 365.101, + "args": { + "External id": 1421352,"Record function id": 0, "Ev Idx": 9255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619709.487, "dur": 5.519, + "args": { + "External id": 1421353,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619718.913, "dur": 1.274, + "args": { + "External id": 1421354,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619722.470, "dur": 1.000, + "args": { + "External id": 1421355,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619725.527, "dur": 1.168, + "args": { + "External id": 1421356,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619729.100, "dur": 0.972, + "args": { + "External id": 1421357,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619731.758, "dur": 3.171, + "args": { + "External id": 1421358,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619737.113, "dur": 1.054, + "args": { + "External id": 1421359,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619740.349, "dur": 2.058, + "args": { + "External id": 1421360,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619746.384, "dur": 0.860, + "args": { + "External id": 1421361,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535619748.942, "dur": 1.051, + "args": { + "External id": 1421362,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535619771.691, "dur": 168.566, + "args": { + "External id": 1421363,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535619792.729, "dur": 141.587, + "args": { + "External id": 1421364,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535619811.289, "dur": 15.840, + "args": { + "External id": 1421365,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535619831.688, "dur": 73.516, + "args": { + "External id": 1421366,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535619835.051, "dur": 69.784, + "args": { + "External id": 1421367,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535619839.420, "dur": 6.470, + "args": { + "External id": 1421368,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535619848.301, "dur": 55.631, + "args": { + "External id": 1421369,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9272 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.13", "pid": 2338710, "tid": 2379450, + "ts": 6410535620118.515, "dur": 718.774, + "args": { + "External id": 1421370,"Record function id": 0, "Ev Idx": 9273 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410535620139.357, "dur": 682.165, + "args": { + "External id": 1421371,"Record function id": 0, "Ev Idx": 9274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535620219.114, "dur": 6.801, + "args": { + "External id": 1421372,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535620246.640, "dur": 35.895, + "args": { + "External id": 1421373,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620252.984, "dur": 4.050, + "args": { + "External id": 1421374,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620259.587, "dur": 0.464, + "args": { + "External id": 1421375,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620261.664, "dur": 0.609, + "args": { + "External id": 1421376,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620263.901, "dur": 0.728, + "args": { + "External id": 1421377,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620266.381, "dur": 0.620, + "args": { + "External id": 1421378,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620268.733, "dur": 0.492, + "args": { + "External id": 1421379,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620270.972, "dur": 0.456, + "args": { + "External id": 1421380,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620273.533, "dur": 0.368, + "args": { + "External id": 1421381,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620275.058, "dur": 2.827, + "args": { + "External id": 1421382,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535620298.621, "dur": 56.562, + "args": { + "External id": 1421383,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535620393.870, "dur": 157.121, + "args": { + "External id": 1421384,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535620410.068, "dur": 3.562, + "args": { + "External id": 1421385,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535620438.152, "dur": 13.976, + "args": { + "External id": 1421386,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535620443.239, "dur": 8.358, + "args": { + "External id": 1421387,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620448.275, "dur": 1.172, + "args": { + "External id": 1421388,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535620461.735, "dur": 28.980, + "args": { + "External id": 1421389,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620464.488, "dur": 0.574, + "args": { + "External id": 1421390,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620466.801, "dur": 0.573, + "args": { + "External id": 1421391,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620469.646, "dur": 0.563, + "args": { + "External id": 1421392,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620472.265, "dur": 0.435, + "args": { + "External id": 1421393,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620473.911, "dur": 0.756, + "args": { + "External id": 1421394,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620477.028, "dur": 3.139, + "args": { + "External id": 1421395,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620482.156, "dur": 0.477, + "args": { + "External id": 1421396,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620483.859, "dur": 0.451, + "args": { + "External id": 1421397,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535620486.565, "dur": 0.461, + "args": { + "External id": 1421398,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535620503.993, "dur": 37.305, + "args": { + "External id": 1421399,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535620605.802, "dur": 134.003, + "args": { + "External id": 1421400,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535620634.235, "dur": 101.794, + "args": { + "External id": 1421401,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9304, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535620645.802, "dur": 85.392, + "args": { + "External id": 1421402,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535620758.318, "dur": 2.573, + "args": { + "External id": 1421403,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9306, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535620854.604, "dur": 2253.368, + "args": { + "External id": 1421404,"Sequence number": 15109101, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9307 + } + }, + { + "ph": "f", "id": 418, "pid": 2338710, "tid": 2379450, "ts": 6410535620854.604, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535620987.783, "dur": 172.734, + "args": { + "External id": 1421405,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535621219.356, "dur": 48.534, + "args": { + "External id": 1421406,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535621289.538, "dur": 81.023, + "args": { + "External id": 1421407,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535621388.018, "dur": 78.965, + "args": { + "External id": 1421408,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535621483.551, "dur": 45.146, + "args": { + "External id": 1421409,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535621540.915, "dur": 33.241, + "args": { + "External id": 1421410,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535621582.999, "dur": 33.428, + "args": { + "External id": 1421411,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535621653.266, "dur": 32.208, + "args": { + "External id": 1421412,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535621710.183, "dur": 31.763, + "args": { + "External id": 1421413,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535621770.584, "dur": 22.220, + "args": { + "External id": 1421414,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535621813.146, "dur": 17.834, + "args": { + "External id": 1421415,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535621857.568, "dur": 56.885, + "args": { + "External id": 1421416,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535621919.645, "dur": 39.098, + "args": { + "External id": 1421417,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535622000.136, "dur": 363.865, + "args": { + "External id": 1421418,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535622158.047, "dur": 11.390, + "args": { + "External id": 1421419,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535622172.714, "dur": 3.471, + "args": { + "External id": 1421420,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535622178.437, "dur": 2.959, + "args": { + "External id": 1421421,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535622182.994, "dur": 3.298, + "args": { + "External id": 1421422,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535622242.113, "dur": 6.305, + "args": { + "External id": 1421423,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535622244.604, "dur": 3.567, + "args": { + "External id": 1421424,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535622250.608, "dur": 37.652, + "args": { + "External id": 1421425,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535622257.367, "dur": 2.315, + "args": { + "External id": 1421426,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535622289.869, "dur": 2.136, + "args": { + "External id": 1421427,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535622291.250, "dur": 0.617, + "args": { + "External id": 1421428,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535622293.665, "dur": 16.760, + "args": { + "External id": 1421429,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535622296.267, "dur": 0.742, + "args": { + "External id": 1421430,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535622407.359, "dur": 55.219, + "args": { + "External id": 1421431,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535622487.151, "dur": 20.439, + "args": { + "External id": 1421432,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535622519.114, "dur": 58.732, + "args": { + "External id": 1421433,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535622589.398, "dur": 46.294, + "args": { + "External id": 1421434,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535622656.359, "dur": 27.045, + "args": { + "External id": 1421435,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535622692.145, "dur": 35.948, + "args": { + "External id": 1421436,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535622737.960, "dur": 32.266, + "args": { + "External id": 1421437,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535622779.589, "dur": 35.043, + "args": { + "External id": 1421438,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535622841.966, "dur": 30.440, + "args": { + "External id": 1421439,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535622894.102, "dur": 29.877, + "args": { + "External id": 1421440,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535622943.399, "dur": 20.603, + "args": { + "External id": 1421441,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535622982.528, "dur": 16.874, + "args": { + "External id": 1421442,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535623014.270, "dur": 18.935, + "args": { + "External id": 1421443,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623164.959, "dur": 19.222, + "args": { + "External id": 1421444,"Record function id": 0, "Ev Idx": 9347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623169.393, "dur": 13.541, + "args": { + "External id": 1421445,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623174.314, "dur": 7.373, + "args": { + "External id": 1421446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623176.607, "dur": 4.931, + "args": { + "External id": 1421447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623189.088, "dur": 9.106, + "args": { + "External id": 1421448,"Record function id": 0, "Ev Idx": 9351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623190.939, "dur": 6.534, + "args": { + "External id": 1421449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623191.774, "dur": 5.099, + "args": { + "External id": 1421450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623192.814, "dur": 3.921, + "args": { + "External id": 1421451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623202.309, "dur": 5.547, + "args": { + "External id": 1421452,"Record function id": 0, "Ev Idx": 9355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623203.738, "dur": 3.564, + "args": { + "External id": 1421453,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623204.562, "dur": 2.212, + "args": { + "External id": 1421454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623205.338, "dur": 1.355, + "args": { + "External id": 1421455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623212.021, "dur": 4.594, + "args": { + "External id": 1421456,"Record function id": 0, "Ev Idx": 9359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623213.370, "dur": 2.751, + "args": { + "External id": 1421457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623214.155, "dur": 1.383, + "args": { + "External id": 1421458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623214.643, "dur": 0.815, + "args": { + "External id": 1421459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623220.476, "dur": 4.892, + "args": { + "External id": 1421460,"Record function id": 0, "Ev Idx": 9363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623222.135, "dur": 2.745, + "args": { + "External id": 1421461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623222.693, "dur": 1.390, + "args": { + "External id": 1421462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623223.214, "dur": 0.742, + "args": { + "External id": 1421463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623229.299, "dur": 4.970, + "args": { + "External id": 1421464,"Record function id": 0, "Ev Idx": 9367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623230.557, "dur": 3.129, + "args": { + "External id": 1421465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623231.306, "dur": 1.628, + "args": { + "External id": 1421466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623232.082, "dur": 0.715, + "args": { + "External id": 1421467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623238.332, "dur": 4.854, + "args": { + "External id": 1421468,"Record function id": 0, "Ev Idx": 9371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623240.018, "dur": 2.666, + "args": { + "External id": 1421469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623240.647, "dur": 1.407, + "args": { + "External id": 1421470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623241.135, "dur": 0.817, + "args": { + "External id": 1421471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623246.959, "dur": 4.288, + "args": { + "External id": 1421472,"Record function id": 0, "Ev Idx": 9375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623248.352, "dur": 2.428, + "args": { + "External id": 1421473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623248.973, "dur": 1.274, + "args": { + "External id": 1421474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623249.340, "dur": 0.794, + "args": { + "External id": 1421475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623254.996, "dur": 6.867, + "args": { + "External id": 1421476,"Record function id": 0, "Ev Idx": 9379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535623256.441, "dur": 4.902, + "args": { + "External id": 1421477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623257.046, "dur": 3.596, + "args": { + "External id": 1421478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535623257.734, "dur": 2.759, + "args": { + "External id": 1421479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535623266.695, "dur": 62084.462, + "args": { + "External id": 1421480,"Record function id": 0, "Sequence number": 15109100, "Fwd thread id": 1, "Ev Idx": 9383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535623268.333, "dur": 62072.277, + "args": { + "External id": 1421481,"Sequence number": 15109100, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9384 + } + }, + { + "ph": "f", "id": 419, "pid": 2338710, "tid": 2379450, "ts": 6410535623268.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410535623305.493, "dur": 49.367, + "args": { + "External id": 1421482,"Record function id": 0, "Ev Idx": 9385 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410535623364.833, "dur": 99.170, + "args": { + "External id": 1421483,"Record function id": 0, "Ev Idx": 9386 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 2338710, "tid": 2379450, + "ts": 6410535623473.902, "dur": 61856.108, + "args": { + "External id": 1421484,"Record function id": 0, "Ev Idx": 9387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535623588.308, "dur": 9.133, + "args": { + "External id": 1421485,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535623610.042, "dur": 13.541, + "args": { + "External id": 1421486,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535623649.471, "dur": 60576.904, + "args": { + "External id": 1421487,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535623667.759, "dur": 60544.268, + "args": { + "External id": 1421488,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535623787.155, "dur": 21.645, + "args": { + "External id": 1421489,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535623836.125, "dur": 60328.429, + "args": { + "External id": 1421490,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535623839.097, "dur": 60324.490, + "args": { + "External id": 1421491,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535623844.738, "dur": 11.089, + "args": { + "External id": 1421492,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535623858.652, "dur": 60300.998, + "args": { + "External id": 1421493,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535684349.122, "dur": 12.914, + "args": { + "External id": 1421494,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535684352.982, "dur": 8.724, + "args": { + "External id": 1421495,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535684397.396, "dur": 433.479, + "args": { + "External id": 1421496,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535684446.158, "dur": 378.381, + "args": { + "External id": 1421497,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9400, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535684461.362, "dur": 356.715, + "args": { + "External id": 1421498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535684855.426, "dur": 2.580, + "args": { + "External id": 1421499,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9402, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535684930.232, "dur": 7.932, + "args": { + "External id": 1421500,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535684955.086, "dur": 41.465, + "args": { + "External id": 1421501,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685009.652, "dur": 1.797, + "args": { + "External id": 1421502,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685018.082, "dur": 16.120, + "args": { + "External id": 1421503,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685040.707, "dur": 1.389, + "args": { + "External id": 1421504,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685046.686, "dur": 56.592, + "args": { + "External id": 1421505,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685113.861, "dur": 4.192, + "args": { + "External id": 1421506,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685123.552, "dur": 16.140, + "args": { + "External id": 1421507,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685144.624, "dur": 1.184, + "args": { + "External id": 1421508,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685150.242, "dur": 13.311, + "args": { + "External id": 1421509,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685168.442, "dur": 1.349, + "args": { + "External id": 1421510,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685174.482, "dur": 13.399, + "args": { + "External id": 1421511,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685193.018, "dur": 1.005, + "args": { + "External id": 1421512,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685200.628, "dur": 12.919, + "args": { + "External id": 1421513,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685217.876, "dur": 0.974, + "args": { + "External id": 1421514,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685223.263, "dur": 11.785, + "args": { + "External id": 1421515,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685239.736, "dur": 1.281, + "args": { + "External id": 1421516,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685245.249, "dur": 11.506, + "args": { + "External id": 1421517,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535685370.093, "dur": 3482.276, + "args": { + "External id": 1421518,"Record function id": 0, "Ev Idx": 9421 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410535685393.646, "dur": 1309.053, + "args": { + "External id": 1421519,"Record function id": 0, "Ev Idx": 9422 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410535685411.148, "dur": 404.542, + "args": { + "External id": 1421520,"Record function id": 0, "Ev Idx": 9423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685535.415, "dur": 6.034, + "args": { + "External id": 1421521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685545.772, "dur": 1.463, + "args": { + "External id": 1421522,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685550.032, "dur": 3.717, + "args": { + "External id": 1421523,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685555.864, "dur": 1.210, + "args": { + "External id": 1421524,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685561.133, "dur": 1.168, + "args": { + "External id": 1421525,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685564.215, "dur": 0.922, + "args": { + "External id": 1421526,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685566.862, "dur": 0.986, + "args": { + "External id": 1421527,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685569.829, "dur": 2.493, + "args": { + "External id": 1421528,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685577.009, "dur": 0.962, + "args": { + "External id": 1421529,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535685579.448, "dur": 0.663, + "args": { + "External id": 1421530,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535685601.269, "dur": 174.707, + "args": { + "External id": 1421531,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535685621.938, "dur": 148.437, + "args": { + "External id": 1421532,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535685640.568, "dur": 20.008, + "args": { + "External id": 1421533,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535685665.324, "dur": 74.338, + "args": { + "External id": 1421534,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535685668.653, "dur": 70.583, + "args": { + "External id": 1421535,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535685673.392, "dur": 5.764, + "args": { + "External id": 1421536,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535685681.356, "dur": 57.136, + "args": { + "External id": 1421537,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9440 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.12", "pid": 2338710, "tid": 2379450, + "ts": 6410535685915.796, "dur": 777.889, + "args": { + "External id": 1421538,"Record function id": 0, "Ev Idx": 9441 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410535685937.076, "dur": 741.135, + "args": { + "External id": 1421539,"Record function id": 0, "Ev Idx": 9442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535686008.325, "dur": 5.488, + "args": { + "External id": 1421540,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535686030.845, "dur": 94.183, + "args": { + "External id": 1421541,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686036.568, "dur": 2.060, + "args": { + "External id": 1421542,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686041.540, "dur": 0.713, + "args": { + "External id": 1421543,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686044.709, "dur": 0.505, + "args": { + "External id": 1421544,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686046.503, "dur": 0.707, + "args": { + "External id": 1421545,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686049.296, "dur": 0.573, + "args": { + "External id": 1421546,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686051.773, "dur": 58.803, + "args": { + "External id": 1421547,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686113.923, "dur": 0.807, + "args": { + "External id": 1421548,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686116.785, "dur": 0.523, + "args": { + "External id": 1421549,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686119.029, "dur": 0.747, + "args": { + "External id": 1421550,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535686139.713, "dur": 52.926, + "args": { + "External id": 1421551,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535686233.068, "dur": 140.710, + "args": { + "External id": 1421552,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535686246.559, "dur": 4.849, + "args": { + "External id": 1421553,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535686257.812, "dur": 12.532, + "args": { + "External id": 1421554,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535686262.842, "dur": 7.028, + "args": { + "External id": 1421555,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686267.409, "dur": 0.935, + "args": { + "External id": 1421556,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535686279.568, "dur": 34.400, + "args": { + "External id": 1421557,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686282.459, "dur": 0.758, + "args": { + "External id": 1421558,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686284.838, "dur": 0.594, + "args": { + "External id": 1421559,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686287.493, "dur": 3.448, + "args": { + "External id": 1421560,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686293.022, "dur": 0.541, + "args": { + "External id": 1421561,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686294.768, "dur": 0.550, + "args": { + "External id": 1421562,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686303.520, "dur": 0.498, + "args": { + "External id": 1421563,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686305.617, "dur": 0.471, + "args": { + "External id": 1421564,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686307.748, "dur": 0.475, + "args": { + "External id": 1421565,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535686309.739, "dur": 0.495, + "args": { + "External id": 1421566,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535686329.825, "dur": 34.583, + "args": { + "External id": 1421567,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535686452.875, "dur": 139.690, + "args": { + "External id": 1421568,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535686484.197, "dur": 104.288, + "args": { + "External id": 1421569,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9472, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535686496.662, "dur": 86.916, + "args": { + "External id": 1421570,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535686611.157, "dur": 2.194, + "args": { + "External id": 1421571,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9474, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535686711.547, "dur": 2116.045, + "args": { + "External id": 1421572,"Sequence number": 15109099, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9475 + } + }, + { + "ph": "f", "id": 420, "pid": 2338710, "tid": 2379450, "ts": 6410535686711.547, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535686846.065, "dur": 119.989, + "args": { + "External id": 1421573,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535687014.656, "dur": 90.341, + "args": { + "External id": 1421574,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535687130.182, "dur": 66.475, + "args": { + "External id": 1421575,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535687210.236, "dur": 36.953, + "args": { + "External id": 1421576,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535687254.216, "dur": 36.544, + "args": { + "External id": 1421577,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535687297.933, "dur": 32.423, + "args": { + "External id": 1421578,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535687337.698, "dur": 33.831, + "args": { + "External id": 1421579,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535687409.959, "dur": 46.294, + "args": { + "External id": 1421580,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535687482.287, "dur": 33.587, + "args": { + "External id": 1421581,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535687544.045, "dur": 22.523, + "args": { + "External id": 1421582,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535687584.068, "dur": 17.575, + "args": { + "External id": 1421583,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535687612.616, "dur": 50.197, + "args": { + "External id": 1421584,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535687667.770, "dur": 38.604, + "args": { + "External id": 1421585,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535687741.906, "dur": 368.142, + "args": { + "External id": 1421586,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535687858.359, "dur": 9.369, + "args": { + "External id": 1421587,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535687870.699, "dur": 6.695, + "args": { + "External id": 1421588,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535687879.173, "dur": 2.157, + "args": { + "External id": 1421589,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535687883.097, "dur": 2.400, + "args": { + "External id": 1421590,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535687938.014, "dur": 6.125, + "args": { + "External id": 1421591,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535687940.312, "dur": 3.625, + "args": { + "External id": 1421592,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535687946.309, "dur": 41.656, + "args": { + "External id": 1421593,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535687953.135, "dur": 4.490, + "args": { + "External id": 1421594,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535687993.052, "dur": 2.352, + "args": { + "External id": 1421595,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535687994.520, "dur": 0.733, + "args": { + "External id": 1421596,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535687996.973, "dur": 18.464, + "args": { + "External id": 1421597,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535687999.300, "dur": 0.610, + "args": { + "External id": 1421598,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535688157.571, "dur": 39.966, + "args": { + "External id": 1421599,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535688226.995, "dur": 21.613, + "args": { + "External id": 1421600,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535688259.534, "dur": 63.622, + "args": { + "External id": 1421601,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535688332.203, "dur": 50.571, + "args": { + "External id": 1421602,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535688395.954, "dur": 46.182, + "args": { + "External id": 1421603,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535688454.412, "dur": 42.179, + "args": { + "External id": 1421604,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535688505.434, "dur": 34.731, + "args": { + "External id": 1421605,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535688549.468, "dur": 35.497, + "args": { + "External id": 1421606,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535688609.616, "dur": 30.332, + "args": { + "External id": 1421607,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535688659.398, "dur": 28.375, + "args": { + "External id": 1421608,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535688704.722, "dur": 19.604, + "args": { + "External id": 1421609,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535688741.603, "dur": 16.419, + "args": { + "External id": 1421610,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535688772.368, "dur": 17.730, + "args": { + "External id": 1421611,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688877.618, "dur": 18.002, + "args": { + "External id": 1421612,"Record function id": 0, "Ev Idx": 9515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688881.315, "dur": 13.099, + "args": { + "External id": 1421613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688886.208, "dur": 7.007, + "args": { + "External id": 1421614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688888.296, "dur": 4.774, + "args": { + "External id": 1421615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688900.219, "dur": 5.979, + "args": { + "External id": 1421616,"Record function id": 0, "Ev Idx": 9519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688901.549, "dur": 4.053, + "args": { + "External id": 1421617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688902.566, "dur": 2.349, + "args": { + "External id": 1421618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688903.445, "dur": 1.337, + "args": { + "External id": 1421619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688910.219, "dur": 5.140, + "args": { + "External id": 1421620,"Record function id": 0, "Ev Idx": 9523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688911.989, "dur": 2.889, + "args": { + "External id": 1421621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688912.579, "dur": 1.796, + "args": { + "External id": 1421622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688913.109, "dur": 1.166, + "args": { + "External id": 1421623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688919.137, "dur": 4.339, + "args": { + "External id": 1421624,"Record function id": 0, "Ev Idx": 9527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688920.271, "dur": 2.711, + "args": { + "External id": 1421625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688920.944, "dur": 1.525, + "args": { + "External id": 1421626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688921.657, "dur": 0.724, + "args": { + "External id": 1421627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688927.118, "dur": 6.725, + "args": { + "External id": 1421628,"Record function id": 0, "Ev Idx": 9531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688928.373, "dur": 4.947, + "args": { + "External id": 1421629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688929.085, "dur": 3.628, + "args": { + "External id": 1421630,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688929.590, "dur": 3.051, + "args": { + "External id": 1421631,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688937.613, "dur": 4.962, + "args": { + "External id": 1421632,"Record function id": 0, "Ev Idx": 9535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688939.262, "dur": 2.769, + "args": { + "External id": 1421633,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688939.999, "dur": 1.520, + "args": { + "External id": 1421634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688940.471, "dur": 0.943, + "args": { + "External id": 1421635,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688946.375, "dur": 3.887, + "args": { + "External id": 1421636,"Record function id": 0, "Ev Idx": 9539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688947.467, "dur": 2.303, + "args": { + "External id": 1421637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688948.019, "dur": 1.244, + "args": { + "External id": 1421638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688948.351, "dur": 0.783, + "args": { + "External id": 1421639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688953.872, "dur": 3.932, + "args": { + "External id": 1421640,"Record function id": 0, "Ev Idx": 9543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688954.925, "dur": 2.363, + "args": { + "External id": 1421641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688955.625, "dur": 1.165, + "args": { + "External id": 1421642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688955.955, "dur": 0.714, + "args": { + "External id": 1421643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688961.694, "dur": 4.828, + "args": { + "External id": 1421644,"Record function id": 0, "Ev Idx": 9547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535688963.022, "dur": 2.980, + "args": { + "External id": 1421645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688963.835, "dur": 1.688, + "args": { + "External id": 1421646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535688964.640, "dur": 0.749, + "args": { + "External id": 1421647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535688974.109, "dur": 62064.575, + "args": { + "External id": 1421648,"Record function id": 0, "Sequence number": 15109098, "Fwd thread id": 1, "Ev Idx": 9551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535688975.836, "dur": 62052.121, + "args": { + "External id": 1421649,"Sequence number": 15109098, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9552 + } + }, + { + "ph": "f", "id": 421, "pid": 2338710, "tid": 2379450, "ts": 6410535688975.836, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410535689009.159, "dur": 90.135, + "args": { + "External id": 1421650,"Record function id": 0, "Ev Idx": 9553 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410535689112.036, "dur": 78.282, + "args": { + "External id": 1421651,"Record function id": 0, "Ev Idx": 9554 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 2338710, "tid": 2379450, + "ts": 6410535689196.915, "dur": 61821.960, + "args": { + "External id": 1421652,"Record function id": 0, "Ev Idx": 9555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535689305.533, "dur": 8.610, + "args": { + "External id": 1421653,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535689326.518, "dur": 6.101, + "args": { + "External id": 1421654,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535689349.163, "dur": 60667.956, + "args": { + "External id": 1421655,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535689365.681, "dur": 60636.577, + "args": { + "External id": 1421656,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535689517.655, "dur": 25.621, + "args": { + "External id": 1421657,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535689567.297, "dur": 60388.299, + "args": { + "External id": 1421658,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535689573.630, "dur": 60381.128, + "args": { + "External id": 1421659,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535689579.032, "dur": 15.278, + "args": { + "External id": 1421660,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535689599.709, "dur": 60351.613, + "args": { + "External id": 1421661,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535750174.021, "dur": 15.801, + "args": { + "External id": 1421662,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535750177.959, "dur": 11.079, + "args": { + "External id": 1421663,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750226.755, "dur": 350.224, + "args": { + "External id": 1421664,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535750259.770, "dur": 311.172, + "args": { + "External id": 1421665,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9568, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535750275.295, "dur": 288.908, + "args": { + "External id": 1421666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535750602.289, "dur": 2.743, + "args": { + "External id": 1421667,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9570, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750675.589, "dur": 10.115, + "args": { + "External id": 1421668,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750702.169, "dur": 40.871, + "args": { + "External id": 1421669,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750755.540, "dur": 1.901, + "args": { + "External id": 1421670,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750763.432, "dur": 16.002, + "args": { + "External id": 1421671,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750786.345, "dur": 1.274, + "args": { + "External id": 1421672,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750792.971, "dur": 13.176, + "args": { + "External id": 1421673,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750812.538, "dur": 1.165, + "args": { + "External id": 1421674,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750817.770, "dur": 13.992, + "args": { + "External id": 1421675,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750837.370, "dur": 0.923, + "args": { + "External id": 1421676,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750842.860, "dur": 12.164, + "args": { + "External id": 1421677,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750859.963, "dur": 1.308, + "args": { + "External id": 1421678,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750865.479, "dur": 12.641, + "args": { + "External id": 1421679,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750883.779, "dur": 0.882, + "args": { + "External id": 1421680,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750888.970, "dur": 11.500, + "args": { + "External id": 1421681,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750905.328, "dur": 0.913, + "args": { + "External id": 1421682,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750910.992, "dur": 12.790, + "args": { + "External id": 1421683,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535750929.440, "dur": 3.219, + "args": { + "External id": 1421684,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535750938.770, "dur": 12.449, + "args": { + "External id": 1421685,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535751091.579, "dur": 3437.975, + "args": { + "External id": 1421686,"Record function id": 0, "Ev Idx": 9589 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410535751119.259, "dur": 1238.094, + "args": { + "External id": 1421687,"Record function id": 0, "Ev Idx": 9590 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410535751136.843, "dur": 400.630, + "args": { + "External id": 1421688,"Record function id": 0, "Ev Idx": 9591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751242.493, "dur": 5.590, + "args": { + "External id": 1421689,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751251.824, "dur": 1.062, + "args": { + "External id": 1421690,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751255.432, "dur": 1.285, + "args": { + "External id": 1421691,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751258.483, "dur": 1.242, + "args": { + "External id": 1421692,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751261.709, "dur": 0.896, + "args": { + "External id": 1421693,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751264.082, "dur": 1.176, + "args": { + "External id": 1421694,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751266.895, "dur": 0.984, + "args": { + "External id": 1421695,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751269.770, "dur": 4.578, + "args": { + "External id": 1421696,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751276.540, "dur": 1.078, + "args": { + "External id": 1421697,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535751281.251, "dur": 0.924, + "args": { + "External id": 1421698,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535751302.790, "dur": 192.540, + "args": { + "External id": 1421699,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535751323.037, "dur": 165.712, + "args": { + "External id": 1421700,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535751341.619, "dur": 17.568, + "args": { + "External id": 1421701,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535751363.891, "dur": 92.883, + "args": { + "External id": 1421702,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535751366.981, "dur": 89.295, + "args": { + "External id": 1421703,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751371.731, "dur": 6.400, + "args": { + "External id": 1421704,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535751380.481, "dur": 74.403, + "args": { + "External id": 1421705,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9608 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.11", "pid": 2338710, "tid": 2379450, + "ts": 6410535751644.670, "dur": 702.937, + "args": { + "External id": 1421706,"Record function id": 0, "Ev Idx": 9609 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410535751665.625, "dur": 667.036, + "args": { + "External id": 1421707,"Record function id": 0, "Ev Idx": 9610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535751738.252, "dur": 6.433, + "args": { + "External id": 1421708,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535751762.362, "dur": 32.929, + "args": { + "External id": 1421709,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751767.885, "dur": 1.893, + "args": { + "External id": 1421710,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751772.059, "dur": 0.812, + "args": { + "External id": 1421711,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751774.512, "dur": 2.616, + "args": { + "External id": 1421712,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751779.347, "dur": 0.484, + "args": { + "External id": 1421713,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751781.443, "dur": 0.758, + "args": { + "External id": 1421714,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751784.590, "dur": 0.472, + "args": { + "External id": 1421715,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751786.494, "dur": 0.364, + "args": { + "External id": 1421716,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751788.791, "dur": 0.508, + "args": { + "External id": 1421717,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751790.905, "dur": 0.366, + "args": { + "External id": 1421718,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535751807.247, "dur": 45.810, + "args": { + "External id": 1421719,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535751888.395, "dur": 122.758, + "args": { + "External id": 1421720,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535751901.193, "dur": 3.416, + "args": { + "External id": 1421721,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535751911.477, "dur": 13.803, + "args": { + "External id": 1421722,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535751916.460, "dur": 8.311, + "args": { + "External id": 1421723,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751920.501, "dur": 2.734, + "args": { + "External id": 1421724,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535751933.211, "dur": 24.924, + "args": { + "External id": 1421725,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751936.213, "dur": 0.512, + "args": { + "External id": 1421726,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751938.122, "dur": 0.647, + "args": { + "External id": 1421727,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751940.215, "dur": 0.687, + "args": { + "External id": 1421728,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751942.405, "dur": 0.507, + "args": { + "External id": 1421729,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751944.196, "dur": 0.651, + "args": { + "External id": 1421730,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751946.833, "dur": 0.593, + "args": { + "External id": 1421731,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751949.032, "dur": 0.381, + "args": { + "External id": 1421732,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751950.413, "dur": 2.512, + "args": { + "External id": 1421733,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535751954.425, "dur": 0.448, + "args": { + "External id": 1421734,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535751970.159, "dur": 32.370, + "args": { + "External id": 1421735,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535752104.272, "dur": 139.194, + "args": { + "External id": 1421736,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535752133.803, "dur": 105.227, + "args": { + "External id": 1421737,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9640, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535752146.239, "dur": 87.659, + "args": { + "External id": 1421738,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535752263.909, "dur": 2.317, + "args": { + "External id": 1421739,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9642, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535752365.959, "dur": 2137.303, + "args": { + "External id": 1421740,"Sequence number": 15109097, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9643 + } + }, + { + "ph": "f", "id": 422, "pid": 2338710, "tid": 2379450, "ts": 6410535752365.959, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535752515.517, "dur": 122.791, + "args": { + "External id": 1421741,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535752688.900, "dur": 49.294, + "args": { + "External id": 1421742,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535752761.230, "dur": 56.637, + "args": { + "External id": 1421743,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535752829.384, "dur": 36.122, + "args": { + "External id": 1421744,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535752872.867, "dur": 36.368, + "args": { + "External id": 1421745,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535752916.821, "dur": 30.382, + "args": { + "External id": 1421746,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535752957.272, "dur": 35.828, + "args": { + "External id": 1421747,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535753021.607, "dur": 31.883, + "args": { + "External id": 1421748,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535753118.415, "dur": 36.681, + "args": { + "External id": 1421749,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535753182.025, "dur": 24.605, + "args": { + "External id": 1421750,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535753222.890, "dur": 18.813, + "args": { + "External id": 1421751,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535753254.965, "dur": 53.042, + "args": { + "External id": 1421752,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535753312.661, "dur": 40.077, + "args": { + "External id": 1421753,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535753386.199, "dur": 330.043, + "args": { + "External id": 1421754,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535753499.722, "dur": 8.278, + "args": { + "External id": 1421755,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535753510.980, "dur": 3.111, + "args": { + "External id": 1421756,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535753515.935, "dur": 5.209, + "args": { + "External id": 1421757,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535753522.557, "dur": 2.441, + "args": { + "External id": 1421758,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535753578.395, "dur": 5.967, + "args": { + "External id": 1421759,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535753580.860, "dur": 3.306, + "args": { + "External id": 1421760,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535753586.274, "dur": 37.904, + "args": { + "External id": 1421761,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535753592.973, "dur": 2.052, + "args": { + "External id": 1421762,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535753626.342, "dur": 2.146, + "args": { + "External id": 1421763,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535753627.536, "dur": 0.835, + "args": { + "External id": 1421764,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535753629.813, "dur": 18.287, + "args": { + "External id": 1421765,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535753632.501, "dur": 0.677, + "args": { + "External id": 1421766,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535753772.735, "dur": 38.628, + "args": { + "External id": 1421767,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535753833.314, "dur": 24.237, + "args": { + "External id": 1421768,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535753868.222, "dur": 58.980, + "args": { + "External id": 1421769,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535753935.719, "dur": 47.461, + "args": { + "External id": 1421770,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535753996.198, "dur": 27.445, + "args": { + "External id": 1421771,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535754031.765, "dur": 81.907, + "args": { + "External id": 1421772,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535754129.336, "dur": 39.066, + "args": { + "External id": 1421773,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535754177.180, "dur": 36.120, + "args": { + "External id": 1421774,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535754236.982, "dur": 34.014, + "args": { + "External id": 1421775,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535754289.727, "dur": 30.154, + "args": { + "External id": 1421776,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535754340.568, "dur": 22.158, + "args": { + "External id": 1421777,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535754386.909, "dur": 17.671, + "args": { + "External id": 1421778,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535754441.595, "dur": 22.896, + "args": { + "External id": 1421779,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754555.262, "dur": 17.834, + "args": { + "External id": 1421780,"Record function id": 0, "Ev Idx": 9683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754558.908, "dur": 13.077, + "args": { + "External id": 1421781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754563.781, "dur": 7.004, + "args": { + "External id": 1421782,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754566.065, "dur": 4.568, + "args": { + "External id": 1421783,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754577.964, "dur": 6.981, + "args": { + "External id": 1421784,"Record function id": 0, "Ev Idx": 9687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754579.470, "dur": 4.840, + "args": { + "External id": 1421785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754580.548, "dur": 3.138, + "args": { + "External id": 1421786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754582.080, "dur": 1.442, + "args": { + "External id": 1421787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754588.851, "dur": 5.050, + "args": { + "External id": 1421788,"Record function id": 0, "Ev Idx": 9691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754590.011, "dur": 3.394, + "args": { + "External id": 1421789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754590.645, "dur": 2.223, + "args": { + "External id": 1421790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754591.376, "dur": 1.381, + "args": { + "External id": 1421791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754597.624, "dur": 6.921, + "args": { + "External id": 1421792,"Record function id": 0, "Ev Idx": 9695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754598.806, "dur": 5.192, + "args": { + "External id": 1421793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754599.558, "dur": 3.818, + "args": { + "External id": 1421794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754600.076, "dur": 3.179, + "args": { + "External id": 1421795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754608.358, "dur": 4.842, + "args": { + "External id": 1421796,"Record function id": 0, "Ev Idx": 9699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754609.714, "dur": 3.022, + "args": { + "External id": 1421797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754610.390, "dur": 1.644, + "args": { + "External id": 1421798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754610.989, "dur": 0.962, + "args": { + "External id": 1421799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754616.985, "dur": 8.268, + "args": { + "External id": 1421800,"Record function id": 0, "Ev Idx": 9703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754618.490, "dur": 6.246, + "args": { + "External id": 1421801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754619.084, "dur": 1.822, + "args": { + "External id": 1421802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754619.840, "dur": 0.950, + "args": { + "External id": 1421803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754629.047, "dur": 4.575, + "args": { + "External id": 1421804,"Record function id": 0, "Ev Idx": 9707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754630.395, "dur": 2.770, + "args": { + "External id": 1421805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754630.960, "dur": 1.570, + "args": { + "External id": 1421806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754631.610, "dur": 0.822, + "args": { + "External id": 1421807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754637.274, "dur": 4.756, + "args": { + "External id": 1421808,"Record function id": 0, "Ev Idx": 9711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754638.710, "dur": 2.796, + "args": { + "External id": 1421809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754639.568, "dur": 1.279, + "args": { + "External id": 1421810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754639.918, "dur": 0.807, + "args": { + "External id": 1421811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754646.534, "dur": 4.183, + "args": { + "External id": 1421812,"Record function id": 0, "Ev Idx": 9715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535754647.699, "dur": 2.545, + "args": { + "External id": 1421813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754648.288, "dur": 1.449, + "args": { + "External id": 1421814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535754648.873, "dur": 0.731, + "args": { + "External id": 1421815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535754655.234, "dur": 63070.966, + "args": { + "External id": 1421816,"Record function id": 0, "Sequence number": 15109096, "Fwd thread id": 1, "Ev Idx": 9719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535754656.909, "dur": 63058.875, + "args": { + "External id": 1421817,"Sequence number": 15109096, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9720 + } + }, + { + "ph": "f", "id": 423, "pid": 2338710, "tid": 2379450, "ts": 6410535754656.909, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410535754692.594, "dur": 45.415, + "args": { + "External id": 1421818,"Record function id": 0, "Ev Idx": 9721 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410535754747.057, "dur": 76.467, + "args": { + "External id": 1421819,"Record function id": 0, "Ev Idx": 9722 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 2338710, "tid": 2379450, + "ts": 6410535754831.086, "dur": 62875.181, + "args": { + "External id": 1421820,"Record function id": 0, "Ev Idx": 9723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535754934.997, "dur": 8.232, + "args": { + "External id": 1421821,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535754954.481, "dur": 5.270, + "args": { + "External id": 1421822,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535754976.847, "dur": 61546.596, + "args": { + "External id": 1421823,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535754993.738, "dur": 61513.798, + "args": { + "External id": 1421824,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535755171.913, "dur": 23.079, + "args": { + "External id": 1421825,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535755219.698, "dur": 61229.024, + "args": { + "External id": 1421826,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535755222.854, "dur": 61224.538, + "args": { + "External id": 1421827,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535755230.517, "dur": 16.175, + "args": { + "External id": 1421828,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535755249.223, "dur": 61192.313, + "args": { + "External id": 1421829,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535816647.456, "dur": 15.669, + "args": { + "External id": 1421830,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535816651.628, "dur": 11.102, + "args": { + "External id": 1421831,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535816699.671, "dur": 528.262, + "args": { + "External id": 1421832,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535816735.585, "dur": 485.027, + "args": { + "External id": 1421833,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9736, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535816748.870, "dur": 463.588, + "args": { + "External id": 1421834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535817256.936, "dur": 2.989, + "args": { + "External id": 1421835,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9738, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817332.014, "dur": 8.186, + "args": { + "External id": 1421836,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817356.828, "dur": 42.331, + "args": { + "External id": 1421837,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817412.002, "dur": 16.805, + "args": { + "External id": 1421838,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817438.140, "dur": 20.932, + "args": { + "External id": 1421839,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817467.847, "dur": 1.629, + "args": { + "External id": 1421840,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817474.137, "dur": 12.757, + "args": { + "External id": 1421841,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817493.289, "dur": 0.842, + "args": { + "External id": 1421842,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817498.708, "dur": 13.929, + "args": { + "External id": 1421843,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817518.021, "dur": 0.986, + "args": { + "External id": 1421844,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817523.600, "dur": 12.416, + "args": { + "External id": 1421845,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817540.960, "dur": 1.473, + "args": { + "External id": 1421846,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817547.014, "dur": 13.226, + "args": { + "External id": 1421847,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817565.921, "dur": 2.895, + "args": { + "External id": 1421848,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817575.542, "dur": 12.956, + "args": { + "External id": 1421849,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817594.435, "dur": 1.152, + "args": { + "External id": 1421850,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817600.109, "dur": 13.644, + "args": { + "External id": 1421851,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535817619.080, "dur": 0.830, + "args": { + "External id": 1421852,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535817624.267, "dur": 12.354, + "args": { + "External id": 1421853,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535817744.747, "dur": 3409.013, + "args": { + "External id": 1421854,"Record function id": 0, "Ev Idx": 9757 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410535817767.420, "dur": 1240.256, + "args": { + "External id": 1421855,"Record function id": 0, "Ev Idx": 9758 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410535817784.987, "dur": 413.213, + "args": { + "External id": 1421856,"Record function id": 0, "Ev Idx": 9759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817883.105, "dur": 4.902, + "args": { + "External id": 1421857,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817892.046, "dur": 1.068, + "args": { + "External id": 1421858,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817895.483, "dur": 1.118, + "args": { + "External id": 1421859,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817898.706, "dur": 1.033, + "args": { + "External id": 1421860,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817901.910, "dur": 0.994, + "args": { + "External id": 1421861,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817906.797, "dur": 3.272, + "args": { + "External id": 1421862,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817911.818, "dur": 0.861, + "args": { + "External id": 1421863,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817914.316, "dur": 2.180, + "args": { + "External id": 1421864,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817918.185, "dur": 0.976, + "args": { + "External id": 1421865,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535817922.871, "dur": 1.170, + "args": { + "External id": 1421866,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535817948.827, "dur": 209.101, + "args": { + "External id": 1421867,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535817968.708, "dur": 182.783, + "args": { + "External id": 1421868,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535817983.671, "dur": 15.306, + "args": { + "External id": 1421869,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535818003.548, "dur": 115.553, + "args": { + "External id": 1421870,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535818006.954, "dur": 111.642, + "args": { + "External id": 1421871,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818011.722, "dur": 6.490, + "args": { + "External id": 1421872,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535818020.395, "dur": 96.746, + "args": { + "External id": 1421873,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9776 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.10", "pid": 2338710, "tid": 2379450, + "ts": 6410535818303.772, "dur": 694.331, + "args": { + "External id": 1421874,"Record function id": 0, "Ev Idx": 9777 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410535818323.692, "dur": 658.893, + "args": { + "External id": 1421875,"Record function id": 0, "Ev Idx": 9778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535818400.630, "dur": 6.478, + "args": { + "External id": 1421876,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535818442.569, "dur": 36.211, + "args": { + "External id": 1421877,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818449.007, "dur": 4.301, + "args": { + "External id": 1421878,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818455.642, "dur": 0.400, + "args": { + "External id": 1421879,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818458.222, "dur": 0.488, + "args": { + "External id": 1421880,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818460.727, "dur": 0.515, + "args": { + "External id": 1421881,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818462.648, "dur": 0.374, + "args": { + "External id": 1421882,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818464.978, "dur": 0.314, + "args": { + "External id": 1421883,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818467.128, "dur": 0.788, + "args": { + "External id": 1421884,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818469.155, "dur": 0.418, + "args": { + "External id": 1421885,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818471.382, "dur": 2.728, + "args": { + "External id": 1421886,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535818493.192, "dur": 52.507, + "args": { + "External id": 1421887,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535818584.330, "dur": 126.286, + "args": { + "External id": 1421888,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535818597.454, "dur": 4.988, + "args": { + "External id": 1421889,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535818609.522, "dur": 11.921, + "args": { + "External id": 1421890,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535818614.432, "dur": 6.426, + "args": { + "External id": 1421891,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818618.695, "dur": 0.712, + "args": { + "External id": 1421892,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535818629.682, "dur": 26.914, + "args": { + "External id": 1421893,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818631.865, "dur": 0.542, + "args": { + "External id": 1421894,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818633.868, "dur": 0.574, + "args": { + "External id": 1421895,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818636.850, "dur": 0.582, + "args": { + "External id": 1421896,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818639.089, "dur": 0.626, + "args": { + "External id": 1421897,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818640.983, "dur": 0.796, + "args": { + "External id": 1421898,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818643.396, "dur": 2.844, + "args": { + "External id": 1421899,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818648.534, "dur": 0.438, + "args": { + "External id": 1421900,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818650.382, "dur": 0.427, + "args": { + "External id": 1421901,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535818652.616, "dur": 0.483, + "args": { + "External id": 1421902,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535818669.510, "dur": 32.757, + "args": { + "External id": 1421903,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535818767.007, "dur": 135.906, + "args": { + "External id": 1421904,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535818794.916, "dur": 104.241, + "args": { + "External id": 1421905,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9808, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535818806.003, "dur": 88.448, + "args": { + "External id": 1421906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535818923.048, "dur": 2.192, + "args": { + "External id": 1421907,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9810, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535819016.378, "dur": 2110.139, + "args": { + "External id": 1421908,"Sequence number": 15109095, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9811 + } + }, + { + "ph": "f", "id": 424, "pid": 2338710, "tid": 2379450, "ts": 6410535819016.378, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535819188.738, "dur": 125.352, + "args": { + "External id": 1421909,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535819367.339, "dur": 65.955, + "args": { + "External id": 1421910,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535819458.137, "dur": 63.003, + "args": { + "External id": 1421911,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535819533.613, "dur": 35.388, + "args": { + "External id": 1421912,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535819576.640, "dur": 35.704, + "args": { + "External id": 1421913,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535819622.308, "dur": 29.927, + "args": { + "External id": 1421914,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535819659.652, "dur": 31.963, + "args": { + "External id": 1421915,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535819722.464, "dur": 27.403, + "args": { + "External id": 1421916,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535819771.564, "dur": 31.944, + "args": { + "External id": 1421917,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535819828.712, "dur": 24.708, + "args": { + "External id": 1421918,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535819871.367, "dur": 19.209, + "args": { + "External id": 1421919,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535819901.471, "dur": 47.370, + "args": { + "External id": 1421920,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535819953.251, "dur": 41.132, + "args": { + "External id": 1421921,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535820026.761, "dur": 407.906, + "args": { + "External id": 1421922,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535820189.813, "dur": 12.501, + "args": { + "External id": 1421923,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535820205.623, "dur": 3.488, + "args": { + "External id": 1421924,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535820210.715, "dur": 6.036, + "args": { + "External id": 1421925,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535820218.019, "dur": 2.470, + "args": { + "External id": 1421926,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535820281.159, "dur": 6.139, + "args": { + "External id": 1421927,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535820283.695, "dur": 3.384, + "args": { + "External id": 1421928,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535820289.591, "dur": 38.192, + "args": { + "External id": 1421929,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535820295.713, "dur": 2.152, + "args": { + "External id": 1421930,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535820333.192, "dur": 9.593, + "args": { + "External id": 1421931,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535820341.761, "dur": 0.895, + "args": { + "External id": 1421932,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535820344.037, "dur": 19.664, + "args": { + "External id": 1421933,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535820346.603, "dur": 0.630, + "args": { + "External id": 1421934,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535820480.672, "dur": 36.418, + "args": { + "External id": 1421935,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535820536.622, "dur": 20.265, + "args": { + "External id": 1421936,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535820566.962, "dur": 59.936, + "args": { + "External id": 1421937,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535820637.715, "dur": 47.462, + "args": { + "External id": 1421938,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535820695.636, "dur": 24.712, + "args": { + "External id": 1421939,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535820728.191, "dur": 35.336, + "args": { + "External id": 1421940,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535820772.842, "dur": 32.017, + "args": { + "External id": 1421941,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535820813.852, "dur": 34.661, + "args": { + "External id": 1421942,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535820871.302, "dur": 26.665, + "args": { + "External id": 1421943,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535820915.747, "dur": 28.760, + "args": { + "External id": 1421944,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535820961.369, "dur": 22.030, + "args": { + "External id": 1421945,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535820998.993, "dur": 15.715, + "args": { + "External id": 1421946,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535821033.393, "dur": 17.467, + "args": { + "External id": 1421947,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821181.192, "dur": 18.383, + "args": { + "External id": 1421948,"Record function id": 0, "Ev Idx": 9851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821185.166, "dur": 13.205, + "args": { + "External id": 1421949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821190.340, "dur": 6.816, + "args": { + "External id": 1421950,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821192.360, "dur": 4.657, + "args": { + "External id": 1421951,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821204.047, "dur": 9.162, + "args": { + "External id": 1421952,"Record function id": 0, "Ev Idx": 9855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821205.927, "dur": 6.695, + "args": { + "External id": 1421953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821207.005, "dur": 5.094, + "args": { + "External id": 1421954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821207.916, "dur": 4.053, + "args": { + "External id": 1421955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821216.994, "dur": 5.006, + "args": { + "External id": 1421956,"Record function id": 0, "Ev Idx": 9859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821218.422, "dur": 3.093, + "args": { + "External id": 1421957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821218.962, "dur": 2.085, + "args": { + "External id": 1421958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821219.641, "dur": 1.330, + "args": { + "External id": 1421959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821225.763, "dur": 4.508, + "args": { + "External id": 1421960,"Record function id": 0, "Ev Idx": 9863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821226.874, "dur": 2.897, + "args": { + "External id": 1421961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821227.767, "dur": 1.519, + "args": { + "External id": 1421962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821228.346, "dur": 0.864, + "args": { + "External id": 1421963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821234.121, "dur": 5.246, + "args": { + "External id": 1421964,"Record function id": 0, "Ev Idx": 9867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821235.538, "dur": 3.351, + "args": { + "External id": 1421965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821236.573, "dur": 1.575, + "args": { + "External id": 1421966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821237.241, "dur": 0.781, + "args": { + "External id": 1421967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821243.348, "dur": 4.600, + "args": { + "External id": 1421968,"Record function id": 0, "Ev Idx": 9871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821244.661, "dur": 2.766, + "args": { + "External id": 1421969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821245.232, "dur": 1.607, + "args": { + "External id": 1421970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821245.952, "dur": 0.758, + "args": { + "External id": 1421971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821251.762, "dur": 4.274, + "args": { + "External id": 1421972,"Record function id": 0, "Ev Idx": 9875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821253.017, "dur": 2.536, + "args": { + "External id": 1421973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821253.663, "dur": 1.205, + "args": { + "External id": 1421974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821253.997, "dur": 0.732, + "args": { + "External id": 1421975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821259.624, "dur": 4.487, + "args": { + "External id": 1421976,"Record function id": 0, "Ev Idx": 9879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821260.894, "dur": 2.719, + "args": { + "External id": 1421977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821261.586, "dur": 1.274, + "args": { + "External id": 1421978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821261.928, "dur": 0.814, + "args": { + "External id": 1421979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821268.167, "dur": 7.355, + "args": { + "External id": 1421980,"Record function id": 0, "Ev Idx": 9883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535821269.306, "dur": 5.714, + "args": { + "External id": 1421981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821269.981, "dur": 4.348, + "args": { + "External id": 1421982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535821270.734, "dur": 3.468, + "args": { + "External id": 1421983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535821280.435, "dur": 59683.953, + "args": { + "External id": 1421984,"Record function id": 0, "Sequence number": 15109094, "Fwd thread id": 1, "Ev Idx": 9887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535821282.047, "dur": 59672.116, + "args": { + "External id": 1421985,"Sequence number": 15109094, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9888 + } + }, + { + "ph": "f", "id": 425, "pid": 2338710, "tid": 2379450, "ts": 6410535821282.047, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410535821318.086, "dur": 47.080, + "args": { + "External id": 1421986,"Record function id": 0, "Ev Idx": 9889 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410535821377.263, "dur": 103.874, + "args": { + "External id": 1421987,"Record function id": 0, "Ev Idx": 9890 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 2338710, "tid": 2379450, + "ts": 6410535821490.188, "dur": 59455.354, + "args": { + "External id": 1421988,"Record function id": 0, "Ev Idx": 9891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535821599.570, "dur": 8.544, + "args": { + "External id": 1421989,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535821620.135, "dur": 5.686, + "args": { + "External id": 1421990,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535821643.616, "dur": 58186.166, + "args": { + "External id": 1421991,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535821660.735, "dur": 58153.540, + "args": { + "External id": 1421992,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535821792.890, "dur": 26.002, + "args": { + "External id": 1421993,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535821842.320, "dur": 57921.257, + "args": { + "External id": 1421994,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535821845.381, "dur": 57916.974, + "args": { + "External id": 1421995,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535821850.878, "dur": 11.959, + "args": { + "External id": 1421996,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535821865.189, "dur": 57892.686, + "args": { + "External id": 1421997,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535879958.902, "dur": 14.016, + "args": { + "External id": 1421998,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535879962.982, "dur": 9.426, + "args": { + "External id": 1421999,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880008.030, "dur": 477.618, + "args": { + "External id": 1422000,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535880045.083, "dur": 433.977, + "args": { + "External id": 1422001,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9904, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535880095.732, "dur": 376.517, + "args": { + "External id": 1422002,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535880513.270, "dur": 2.727, + "args": { + "External id": 1422003,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9906, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880591.163, "dur": 8.044, + "args": { + "External id": 1422004,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880615.022, "dur": 42.392, + "args": { + "External id": 1422005,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880670.699, "dur": 1.695, + "args": { + "External id": 1422006,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880678.972, "dur": 15.790, + "args": { + "External id": 1422007,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880702.028, "dur": 1.244, + "args": { + "External id": 1422008,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880708.168, "dur": 13.668, + "args": { + "External id": 1422009,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880728.128, "dur": 3.131, + "args": { + "External id": 1422010,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880736.533, "dur": 13.927, + "args": { + "External id": 1422011,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880755.476, "dur": 0.920, + "args": { + "External id": 1422012,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880760.755, "dur": 13.117, + "args": { + "External id": 1422013,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880778.976, "dur": 1.195, + "args": { + "External id": 1422014,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880785.703, "dur": 13.645, + "args": { + "External id": 1422015,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880804.417, "dur": 0.869, + "args": { + "External id": 1422016,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880809.726, "dur": 12.617, + "args": { + "External id": 1422017,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880830.290, "dur": 0.904, + "args": { + "External id": 1422018,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880835.655, "dur": 12.559, + "args": { + "External id": 1422019,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535880853.250, "dur": 1.003, + "args": { + "External id": 1422020,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535880858.925, "dur": 10.672, + "args": { + "External id": 1422021,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535880981.680, "dur": 3467.104, + "args": { + "External id": 1422022,"Record function id": 0, "Ev Idx": 9925 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410535881009.171, "dur": 1301.547, + "args": { + "External id": 1422023,"Record function id": 0, "Ev Idx": 9926 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410535881028.464, "dur": 444.161, + "args": { + "External id": 1422024,"Record function id": 0, "Ev Idx": 9927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881173.762, "dur": 5.956, + "args": { + "External id": 1422025,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881183.804, "dur": 1.048, + "args": { + "External id": 1422026,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881187.432, "dur": 3.501, + "args": { + "External id": 1422027,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881193.487, "dur": 1.062, + "args": { + "External id": 1422028,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881196.664, "dur": 1.165, + "args": { + "External id": 1422029,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881201.808, "dur": 1.112, + "args": { + "External id": 1422030,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881204.781, "dur": 0.708, + "args": { + "External id": 1422031,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881207.567, "dur": 2.239, + "args": { + "External id": 1422032,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881211.276, "dur": 0.995, + "args": { + "External id": 1422033,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535881216.291, "dur": 0.776, + "args": { + "External id": 1422034,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535881238.938, "dur": 174.509, + "args": { + "External id": 1422035,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535881259.513, "dur": 148.395, + "args": { + "External id": 1422036,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535881277.269, "dur": 19.963, + "args": { + "External id": 1422037,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535881301.817, "dur": 75.688, + "args": { + "External id": 1422038,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535881304.964, "dur": 72.046, + "args": { + "External id": 1422039,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881310.111, "dur": 7.090, + "args": { + "External id": 1422040,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535881319.311, "dur": 57.272, + "args": { + "External id": 1422041,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9944 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.9", "pid": 2338710, "tid": 2379450, + "ts": 6410535881578.444, "dur": 722.802, + "args": { + "External id": 1422042,"Record function id": 0, "Ev Idx": 9945 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410535881599.725, "dur": 686.719, + "args": { + "External id": 1422043,"Record function id": 0, "Ev Idx": 9946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535881671.945, "dur": 7.007, + "args": { + "External id": 1422044,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535881699.324, "dur": 35.354, + "args": { + "External id": 1422045,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881705.910, "dur": 1.959, + "args": { + "External id": 1422046,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881710.444, "dur": 0.709, + "args": { + "External id": 1422047,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881713.244, "dur": 0.614, + "args": { + "External id": 1422048,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881715.912, "dur": 0.456, + "args": { + "External id": 1422049,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881717.724, "dur": 0.499, + "args": { + "External id": 1422050,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881720.312, "dur": 2.773, + "args": { + "External id": 1422051,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881724.935, "dur": 0.524, + "args": { + "External id": 1422052,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881726.948, "dur": 0.536, + "args": { + "External id": 1422053,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881729.959, "dur": 0.486, + "args": { + "External id": 1422054,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535881749.479, "dur": 51.146, + "args": { + "External id": 1422055,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535881836.468, "dur": 129.165, + "args": { + "External id": 1422056,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535881849.472, "dur": 3.549, + "args": { + "External id": 1422057,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535881859.661, "dur": 12.724, + "args": { + "External id": 1422058,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535881865.141, "dur": 6.585, + "args": { + "External id": 1422059,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881869.514, "dur": 0.681, + "args": { + "External id": 1422060,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535881883.783, "dur": 26.111, + "args": { + "External id": 1422061,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881886.191, "dur": 0.580, + "args": { + "External id": 1422062,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881888.589, "dur": 0.458, + "args": { + "External id": 1422063,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881890.724, "dur": 2.688, + "args": { + "External id": 1422064,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881894.493, "dur": 0.797, + "args": { + "External id": 1422065,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881897.248, "dur": 0.712, + "args": { + "External id": 1422066,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881899.980, "dur": 0.431, + "args": { + "External id": 1422067,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881901.386, "dur": 0.566, + "args": { + "External id": 1422068,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881903.765, "dur": 0.488, + "args": { + "External id": 1422069,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535881906.245, "dur": 0.423, + "args": { + "External id": 1422070,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535881921.943, "dur": 35.617, + "args": { + "External id": 1422071,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535882016.968, "dur": 179.718, + "args": { + "External id": 1422072,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535882047.266, "dur": 144.607, + "args": { + "External id": 1422073,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9976, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535882100.214, "dur": 86.867, + "args": { + "External id": 1422074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535882219.040, "dur": 2.071, + "args": { + "External id": 1422075,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 9978, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535882319.260, "dur": 2086.249, + "args": { + "External id": 1422076,"Sequence number": 15109093, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9979 + } + }, + { + "ph": "f", "id": 426, "pid": 2338710, "tid": 2379450, "ts": 6410535882319.260, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535882470.446, "dur": 125.505, + "args": { + "External id": 1422077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535882644.814, "dur": 50.399, + "args": { + "External id": 1422078,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535882716.181, "dur": 57.928, + "args": { + "External id": 1422079,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535882788.518, "dur": 36.290, + "args": { + "External id": 1422080,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535882831.930, "dur": 35.418, + "args": { + "External id": 1422081,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535882875.022, "dur": 30.462, + "args": { + "External id": 1422082,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535882913.392, "dur": 32.228, + "args": { + "External id": 1422083,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535882975.655, "dur": 26.846, + "args": { + "External id": 1422084,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535883024.177, "dur": 72.164, + "args": { + "External id": 1422085,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535883130.019, "dur": 28.312, + "args": { + "External id": 1422086,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535883175.648, "dur": 16.876, + "args": { + "External id": 1422087,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535883203.940, "dur": 51.595, + "args": { + "External id": 1422088,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535883260.215, "dur": 39.796, + "args": { + "External id": 1422089,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535883340.629, "dur": 358.454, + "args": { + "External id": 1422090,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535883477.782, "dur": 10.299, + "args": { + "External id": 1422091,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535883491.131, "dur": 3.725, + "args": { + "External id": 1422092,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535883496.164, "dur": 3.235, + "args": { + "External id": 1422093,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535883500.815, "dur": 2.954, + "args": { + "External id": 1422094,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535883564.734, "dur": 6.187, + "args": { + "External id": 1422095,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535883567.084, "dur": 3.628, + "args": { + "External id": 1422096,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535883579.933, "dur": 43.103, + "args": { + "External id": 1422097,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535883586.332, "dur": 4.004, + "args": { + "External id": 1422098,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535883625.028, "dur": 2.434, + "args": { + "External id": 1422099,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535883626.582, "dur": 0.788, + "args": { + "External id": 1422100,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535883628.282, "dur": 18.601, + "args": { + "External id": 1422101,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535883630.652, "dur": 0.771, + "args": { + "External id": 1422102,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535883740.639, "dur": 36.291, + "args": { + "External id": 1422103,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535883797.698, "dur": 21.118, + "args": { + "External id": 1422104,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535883829.368, "dur": 55.998, + "args": { + "External id": 1422105,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535883893.962, "dur": 46.870, + "args": { + "External id": 1422106,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535883954.167, "dur": 25.523, + "args": { + "External id": 1422107,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535883987.177, "dur": 34.756, + "args": { + "External id": 1422108,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535884031.062, "dur": 73.255, + "args": { + "External id": 1422109,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535884119.068, "dur": 39.941, + "args": { + "External id": 1422110,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535884183.637, "dur": 29.067, + "args": { + "External id": 1422111,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535884231.810, "dur": 29.638, + "args": { + "External id": 1422112,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535884278.295, "dur": 19.652, + "args": { + "External id": 1422113,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535884315.175, "dur": 16.444, + "args": { + "External id": 1422114,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535884347.007, "dur": 19.817, + "args": { + "External id": 1422115,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884475.531, "dur": 18.516, + "args": { + "External id": 1422116,"Record function id": 0, "Ev Idx": 10019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884479.570, "dur": 13.339, + "args": { + "External id": 1422117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884484.358, "dur": 7.364, + "args": { + "External id": 1422118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884486.842, "dur": 4.704, + "args": { + "External id": 1422119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884498.782, "dur": 5.523, + "args": { + "External id": 1422120,"Record function id": 0, "Ev Idx": 10023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884500.146, "dur": 3.662, + "args": { + "External id": 1422121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884501.069, "dur": 2.037, + "args": { + "External id": 1422122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884501.833, "dur": 1.132, + "args": { + "External id": 1422123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884508.373, "dur": 5.351, + "args": { + "External id": 1422124,"Record function id": 0, "Ev Idx": 10027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884509.771, "dur": 3.471, + "args": { + "External id": 1422125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884510.576, "dur": 2.150, + "args": { + "External id": 1422126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884511.185, "dur": 1.432, + "args": { + "External id": 1422127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884517.501, "dur": 4.608, + "args": { + "External id": 1422128,"Record function id": 0, "Ev Idx": 10031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884519.011, "dur": 2.630, + "args": { + "External id": 1422129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884519.855, "dur": 1.302, + "args": { + "External id": 1422130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884520.217, "dur": 0.847, + "args": { + "External id": 1422131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884525.802, "dur": 6.976, + "args": { + "External id": 1422132,"Record function id": 0, "Ev Idx": 10035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884527.188, "dur": 5.116, + "args": { + "External id": 1422133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884527.765, "dur": 3.889, + "args": { + "External id": 1422134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884528.115, "dur": 3.422, + "args": { + "External id": 1422135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884536.535, "dur": 4.928, + "args": { + "External id": 1422136,"Record function id": 0, "Ev Idx": 10039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884537.940, "dur": 3.024, + "args": { + "External id": 1422137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884538.605, "dur": 1.780, + "args": { + "External id": 1422138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884539.087, "dur": 1.173, + "args": { + "External id": 1422139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884545.309, "dur": 4.057, + "args": { + "External id": 1422140,"Record function id": 0, "Ev Idx": 10043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884546.498, "dur": 2.389, + "args": { + "External id": 1422141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884547.244, "dur": 1.174, + "args": { + "External id": 1422142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884547.559, "dur": 0.774, + "args": { + "External id": 1422143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884552.977, "dur": 4.569, + "args": { + "External id": 1422144,"Record function id": 0, "Ev Idx": 10047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884554.126, "dur": 2.848, + "args": { + "External id": 1422145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884554.970, "dur": 1.260, + "args": { + "External id": 1422146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884555.284, "dur": 0.809, + "args": { + "External id": 1422147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884561.133, "dur": 5.298, + "args": { + "External id": 1422148,"Record function id": 0, "Ev Idx": 10051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535884562.506, "dur": 3.423, + "args": { + "External id": 1422149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884563.073, "dur": 2.189, + "args": { + "External id": 1422150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535884564.231, "dur": 0.895, + "args": { + "External id": 1422151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535884571.326, "dur": 61917.539, + "args": { + "External id": 1422152,"Record function id": 0, "Sequence number": 15109092, "Fwd thread id": 1, "Ev Idx": 10055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535884572.880, "dur": 61904.712, + "args": { + "External id": 1422153,"Sequence number": 15109092, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10056 + } + }, + { + "ph": "f", "id": 427, "pid": 2338710, "tid": 2379450, "ts": 6410535884572.880, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410535884609.204, "dur": 45.847, + "args": { + "External id": 1422154,"Record function id": 0, "Ev Idx": 10057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410535884664.984, "dur": 74.404, + "args": { + "External id": 1422155,"Record function id": 0, "Ev Idx": 10058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 2338710, "tid": 2379450, + "ts": 6410535884746.150, "dur": 61721.040, + "args": { + "External id": 1422156,"Record function id": 0, "Ev Idx": 10059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535884851.914, "dur": 7.666, + "args": { + "External id": 1422157,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535884871.138, "dur": 5.529, + "args": { + "External id": 1422158,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535884896.073, "dur": 60366.590, + "args": { + "External id": 1422159,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535884912.624, "dur": 60335.243, + "args": { + "External id": 1422160,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535885032.339, "dur": 21.294, + "args": { + "External id": 1422161,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535885137.547, "dur": 60059.674, + "args": { + "External id": 1422162,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535885141.452, "dur": 60054.760, + "args": { + "External id": 1422163,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535885149.326, "dur": 17.341, + "args": { + "External id": 1422164,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535885173.341, "dur": 60018.273, + "args": { + "External id": 1422165,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535945382.940, "dur": 15.840, + "args": { + "External id": 1422166,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535945386.731, "dur": 11.609, + "args": { + "External id": 1422167,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535945449.734, "dur": 468.705, + "args": { + "External id": 1422168,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535945485.129, "dur": 427.492, + "args": { + "External id": 1422169,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10072, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535945501.056, "dur": 404.851, + "args": { + "External id": 1422170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535945953.918, "dur": 2.727, + "args": { + "External id": 1422171,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10074, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946030.234, "dur": 8.304, + "args": { + "External id": 1422172,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946108.654, "dur": 45.697, + "args": { + "External id": 1422173,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946170.101, "dur": 3.248, + "args": { + "External id": 1422174,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946180.541, "dur": 16.609, + "args": { + "External id": 1422175,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946204.616, "dur": 1.183, + "args": { + "External id": 1422176,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946210.903, "dur": 16.155, + "args": { + "External id": 1422177,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946233.188, "dur": 1.415, + "args": { + "External id": 1422178,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946239.535, "dur": 15.029, + "args": { + "External id": 1422179,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946259.955, "dur": 1.407, + "args": { + "External id": 1422180,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946265.905, "dur": 15.487, + "args": { + "External id": 1422181,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946286.828, "dur": 1.473, + "args": { + "External id": 1422182,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946292.585, "dur": 12.058, + "args": { + "External id": 1422183,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946310.573, "dur": 1.026, + "args": { + "External id": 1422184,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946315.925, "dur": 10.722, + "args": { + "External id": 1422185,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946331.830, "dur": 3.355, + "args": { + "External id": 1422186,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946339.712, "dur": 11.686, + "args": { + "External id": 1422187,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946356.959, "dur": 1.070, + "args": { + "External id": 1422188,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946364.705, "dur": 12.679, + "args": { + "External id": 1422189,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535946508.235, "dur": 3393.937, + "args": { + "External id": 1422190,"Record function id": 0, "Ev Idx": 10093 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410535946532.153, "dur": 1234.178, + "args": { + "External id": 1422191,"Record function id": 0, "Ev Idx": 10094 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410535946550.856, "dur": 371.424, + "args": { + "External id": 1422192,"Record function id": 0, "Ev Idx": 10095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946656.357, "dur": 5.779, + "args": { + "External id": 1422193,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946666.297, "dur": 1.534, + "args": { + "External id": 1422194,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946670.086, "dur": 1.256, + "args": { + "External id": 1422195,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946673.682, "dur": 1.090, + "args": { + "External id": 1422196,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946676.518, "dur": 1.601, + "args": { + "External id": 1422197,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946679.696, "dur": 1.173, + "args": { + "External id": 1422198,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946682.649, "dur": 2.753, + "args": { + "External id": 1422199,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946687.036, "dur": 2.455, + "args": { + "External id": 1422200,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946693.230, "dur": 0.790, + "args": { + "External id": 1422201,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535946696.569, "dur": 0.993, + "args": { + "External id": 1422202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535946717.546, "dur": 169.460, + "args": { + "External id": 1422203,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535946736.346, "dur": 145.308, + "args": { + "External id": 1422204,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535946753.012, "dur": 17.613, + "args": { + "External id": 1422205,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535946774.979, "dur": 76.566, + "args": { + "External id": 1422206,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535946778.092, "dur": 73.075, + "args": { + "External id": 1422207,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535946783.135, "dur": 7.037, + "args": { + "External id": 1422208,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535946792.229, "dur": 58.307, + "args": { + "External id": 1422209,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.8", "pid": 2338710, "tid": 2379450, + "ts": 6410535947020.000, "dur": 736.351, + "args": { + "External id": 1422210,"Record function id": 0, "Ev Idx": 10113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410535947038.765, "dur": 702.669, + "args": { + "External id": 1422211,"Record function id": 0, "Ev Idx": 10114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535947162.326, "dur": 8.444, + "args": { + "External id": 1422212,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535947189.773, "dur": 33.775, + "args": { + "External id": 1422213,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947196.000, "dur": 2.210, + "args": { + "External id": 1422214,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947200.893, "dur": 2.641, + "args": { + "External id": 1422215,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947205.219, "dur": 0.372, + "args": { + "External id": 1422216,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947206.987, "dur": 0.466, + "args": { + "External id": 1422217,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947209.664, "dur": 0.633, + "args": { + "External id": 1422218,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947211.893, "dur": 0.667, + "args": { + "External id": 1422219,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947214.009, "dur": 0.524, + "args": { + "External id": 1422220,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947216.294, "dur": 0.526, + "args": { + "External id": 1422221,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947218.438, "dur": 0.507, + "args": { + "External id": 1422222,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535947235.587, "dur": 51.358, + "args": { + "External id": 1422223,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410535947324.061, "dur": 143.259, + "args": { + "External id": 1422224,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535947336.100, "dur": 6.234, + "args": { + "External id": 1422225,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410535947348.645, "dur": 12.371, + "args": { + "External id": 1422226,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410535947353.740, "dur": 6.800, + "args": { + "External id": 1422227,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947358.493, "dur": 0.569, + "args": { + "External id": 1422228,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410535947368.707, "dur": 26.067, + "args": { + "External id": 1422229,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947370.992, "dur": 0.893, + "args": { + "External id": 1422230,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947373.707, "dur": 0.611, + "args": { + "External id": 1422231,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947375.873, "dur": 0.641, + "args": { + "External id": 1422232,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947378.329, "dur": 0.638, + "args": { + "External id": 1422233,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947380.854, "dur": 0.411, + "args": { + "External id": 1422234,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947382.623, "dur": 0.410, + "args": { + "External id": 1422235,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947385.070, "dur": 2.581, + "args": { + "External id": 1422236,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947389.385, "dur": 0.467, + "args": { + "External id": 1422237,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535947391.088, "dur": 0.468, + "args": { + "External id": 1422238,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535947406.569, "dur": 49.325, + "args": { + "External id": 1422239,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410535947522.709, "dur": 132.068, + "args": { + "External id": 1422240,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535947551.274, "dur": 99.375, + "args": { + "External id": 1422241,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10144, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410535947562.947, "dur": 82.967, + "args": { + "External id": 1422242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410535947675.053, "dur": 2.075, + "args": { + "External id": 1422243,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10146, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535947774.805, "dur": 2100.787, + "args": { + "External id": 1422244,"Sequence number": 15109091, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10147 + } + }, + { + "ph": "f", "id": 428, "pid": 2338710, "tid": 2379450, "ts": 6410535947774.805, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535947909.054, "dur": 124.188, + "args": { + "External id": 1422245,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535948127.523, "dur": 50.811, + "args": { + "External id": 1422246,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410535948203.495, "dur": 67.160, + "args": { + "External id": 1422247,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535948282.747, "dur": 37.512, + "args": { + "External id": 1422248,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535948327.409, "dur": 37.378, + "args": { + "External id": 1422249,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535948375.029, "dur": 32.270, + "args": { + "External id": 1422250,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535948434.022, "dur": 38.867, + "args": { + "External id": 1422251,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535948507.417, "dur": 29.219, + "args": { + "External id": 1422252,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410535948559.439, "dur": 33.476, + "args": { + "External id": 1422253,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535948618.808, "dur": 25.068, + "args": { + "External id": 1422254,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535948660.017, "dur": 17.893, + "args": { + "External id": 1422255,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535948690.571, "dur": 45.812, + "args": { + "External id": 1422256,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535948741.765, "dur": 39.785, + "args": { + "External id": 1422257,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410535948828.198, "dur": 363.730, + "args": { + "External id": 1422258,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535948936.373, "dur": 11.900, + "args": { + "External id": 1422259,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535948950.962, "dur": 5.578, + "args": { + "External id": 1422260,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535948958.443, "dur": 2.349, + "args": { + "External id": 1422261,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535948962.038, "dur": 3.105, + "args": { + "External id": 1422262,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535949022.181, "dur": 5.929, + "args": { + "External id": 1422263,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535949024.715, "dur": 3.169, + "args": { + "External id": 1422264,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535949030.516, "dur": 78.159, + "args": { + "External id": 1422265,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535949036.720, "dur": 2.126, + "args": { + "External id": 1422266,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410535949112.373, "dur": 4.240, + "args": { + "External id": 1422267,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535949115.093, "dur": 1.413, + "args": { + "External id": 1422268,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410535949117.759, "dur": 19.834, + "args": { + "External id": 1422269,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535949120.781, "dur": 0.751, + "args": { + "External id": 1422270,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410535949233.465, "dur": 33.655, + "args": { + "External id": 1422271,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535949287.580, "dur": 19.861, + "args": { + "External id": 1422272,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535949318.426, "dur": 61.533, + "args": { + "External id": 1422273,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535949388.920, "dur": 69.591, + "args": { + "External id": 1422274,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535949475.641, "dur": 30.304, + "args": { + "External id": 1422275,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535949513.549, "dur": 37.421, + "args": { + "External id": 1422276,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535949560.283, "dur": 33.891, + "args": { + "External id": 1422277,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410535949603.602, "dur": 34.885, + "args": { + "External id": 1422278,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410535949661.380, "dur": 29.041, + "args": { + "External id": 1422279,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535949708.477, "dur": 28.613, + "args": { + "External id": 1422280,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410535949753.971, "dur": 20.149, + "args": { + "External id": 1422281,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410535949790.585, "dur": 16.516, + "args": { + "External id": 1422282,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410535949821.286, "dur": 17.716, + "args": { + "External id": 1422283,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949928.785, "dur": 18.404, + "args": { + "External id": 1422284,"Record function id": 0, "Ev Idx": 10187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949933.328, "dur": 12.436, + "args": { + "External id": 1422285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949938.353, "dur": 6.368, + "args": { + "External id": 1422286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949940.265, "dur": 4.320, + "args": { + "External id": 1422287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949952.038, "dur": 6.457, + "args": { + "External id": 1422288,"Record function id": 0, "Ev Idx": 10191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949953.418, "dur": 4.537, + "args": { + "External id": 1422289,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949954.412, "dur": 2.900, + "args": { + "External id": 1422290,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949955.769, "dur": 1.432, + "args": { + "External id": 1422291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949962.429, "dur": 5.896, + "args": { + "External id": 1422292,"Record function id": 0, "Ev Idx": 10195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949964.094, "dur": 3.706, + "args": { + "External id": 1422293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949964.708, "dur": 2.527, + "args": { + "External id": 1422294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949965.755, "dur": 1.347, + "args": { + "External id": 1422295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949972.109, "dur": 6.078, + "args": { + "External id": 1422296,"Record function id": 0, "Ev Idx": 10199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949973.650, "dur": 4.071, + "args": { + "External id": 1422297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949974.529, "dur": 2.675, + "args": { + "External id": 1422298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949975.518, "dur": 1.579, + "args": { + "External id": 1422299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949981.920, "dur": 8.751, + "args": { + "External id": 1422300,"Record function id": 0, "Ev Idx": 10203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949983.430, "dur": 6.746, + "args": { + "External id": 1422301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949984.032, "dur": 5.484, + "args": { + "External id": 1422302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949985.471, "dur": 3.944, + "args": { + "External id": 1422303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949994.454, "dur": 6.980, + "args": { + "External id": 1422304,"Record function id": 0, "Ev Idx": 10207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535949996.281, "dur": 4.669, + "args": { + "External id": 1422305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949997.146, "dur": 3.305, + "args": { + "External id": 1422306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535949998.582, "dur": 1.777, + "args": { + "External id": 1422307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535950005.396, "dur": 6.251, + "args": { + "External id": 1422308,"Record function id": 0, "Ev Idx": 10211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535950007.047, "dur": 4.112, + "args": { + "External id": 1422309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535950007.602, "dur": 2.950, + "args": { + "External id": 1422310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535950008.953, "dur": 1.502, + "args": { + "External id": 1422311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535950015.582, "dur": 6.184, + "args": { + "External id": 1422312,"Record function id": 0, "Ev Idx": 10215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535950017.235, "dur": 4.068, + "args": { + "External id": 1422313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535950018.030, "dur": 2.755, + "args": { + "External id": 1422314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535950019.515, "dur": 1.175, + "args": { + "External id": 1422315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535950025.646, "dur": 5.879, + "args": { + "External id": 1422316,"Record function id": 0, "Ev Idx": 10219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410535950027.240, "dur": 3.810, + "args": { + "External id": 1422317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535950027.892, "dur": 2.597, + "args": { + "External id": 1422318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410535950029.086, "dur": 1.309, + "args": { + "External id": 1422319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535950035.896, "dur": 61834.725, + "args": { + "External id": 1422320,"Record function id": 0, "Sequence number": 15109090, "Fwd thread id": 1, "Ev Idx": 10223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410535950038.136, "dur": 61821.473, + "args": { + "External id": 1422321,"Sequence number": 15109090, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10224 + } + }, + { + "ph": "f", "id": 429, "pid": 2338710, "tid": 2379450, "ts": 6410535950038.136, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410535950113.312, "dur": 47.160, + "args": { + "External id": 1422322,"Record function id": 0, "Ev Idx": 10225 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410535950170.802, "dur": 75.481, + "args": { + "External id": 1422323,"Record function id": 0, "Ev Idx": 10226 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 2338710, "tid": 2379450, + "ts": 6410535950253.640, "dur": 61597.184, + "args": { + "External id": 1422324,"Record function id": 0, "Ev Idx": 10227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535950360.469, "dur": 8.597, + "args": { + "External id": 1422325,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410535950381.012, "dur": 5.532, + "args": { + "External id": 1422326,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535950403.100, "dur": 60314.648, + "args": { + "External id": 1422327,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410535950437.173, "dur": 60265.758, + "args": { + "External id": 1422328,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410535950567.398, "dur": 28.392, + "args": { + "External id": 1422329,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410535950622.749, "dur": 60031.248, + "args": { + "External id": 1422330,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410535950626.451, "dur": 60026.487, + "args": { + "External id": 1422331,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410535950632.140, "dur": 16.820, + "args": { + "External id": 1422332,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410535950651.588, "dur": 59996.921, + "args": { + "External id": 1422333,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536010840.371, "dur": 15.324, + "args": { + "External id": 1422334,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536010844.278, "dur": 10.924, + "args": { + "External id": 1422335,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536010891.706, "dur": 481.213, + "args": { + "External id": 1422336,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536010951.471, "dur": 414.648, + "args": { + "External id": 1422337,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10240, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536010965.296, "dur": 393.951, + "args": { + "External id": 1422338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536011401.530, "dur": 2.660, + "args": { + "External id": 1422339,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10242, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011500.059, "dur": 8.224, + "args": { + "External id": 1422340,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011524.746, "dur": 43.380, + "args": { + "External id": 1422341,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011580.626, "dur": 1.924, + "args": { + "External id": 1422342,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011589.111, "dur": 26.080, + "args": { + "External id": 1422343,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011621.919, "dur": 1.313, + "args": { + "External id": 1422344,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011627.855, "dur": 13.450, + "args": { + "External id": 1422345,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011647.297, "dur": 1.240, + "args": { + "External id": 1422346,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011652.677, "dur": 13.410, + "args": { + "External id": 1422347,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011671.706, "dur": 1.035, + "args": { + "External id": 1422348,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011677.358, "dur": 12.790, + "args": { + "External id": 1422349,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011695.079, "dur": 1.273, + "args": { + "External id": 1422350,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011700.773, "dur": 13.458, + "args": { + "External id": 1422351,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011719.459, "dur": 1.171, + "args": { + "External id": 1422352,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011724.276, "dur": 11.965, + "args": { + "External id": 1422353,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011741.623, "dur": 3.792, + "args": { + "External id": 1422354,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011750.369, "dur": 11.997, + "args": { + "External id": 1422355,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536011766.974, "dur": 1.167, + "args": { + "External id": 1422356,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536011772.261, "dur": 11.046, + "args": { + "External id": 1422357,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536011888.486, "dur": 3444.602, + "args": { + "External id": 1422358,"Record function id": 0, "Ev Idx": 10261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410536011910.637, "dur": 1310.497, + "args": { + "External id": 1422359,"Record function id": 0, "Ev Idx": 10262 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410536011928.466, "dur": 427.670, + "args": { + "External id": 1422360,"Record function id": 0, "Ev Idx": 10263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012026.978, "dur": 4.473, + "args": { + "External id": 1422361,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012035.385, "dur": 0.975, + "args": { + "External id": 1422362,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012038.843, "dur": 1.139, + "args": { + "External id": 1422363,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012042.548, "dur": 1.358, + "args": { + "External id": 1422364,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012045.609, "dur": 1.109, + "args": { + "External id": 1422365,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012048.138, "dur": 1.025, + "args": { + "External id": 1422366,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012051.136, "dur": 56.514, + "args": { + "External id": 1422367,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012112.963, "dur": 2.848, + "args": { + "External id": 1422368,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012119.978, "dur": 1.068, + "args": { + "External id": 1422369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536012123.444, "dur": 0.876, + "args": { + "External id": 1422370,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536012146.959, "dur": 171.782, + "args": { + "External id": 1422371,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536012166.537, "dur": 146.956, + "args": { + "External id": 1422372,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536012183.397, "dur": 18.097, + "args": { + "External id": 1422373,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536012205.884, "dur": 78.698, + "args": { + "External id": 1422374,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536012209.289, "dur": 74.724, + "args": { + "External id": 1422375,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012214.451, "dur": 7.359, + "args": { + "External id": 1422376,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536012225.637, "dur": 57.653, + "args": { + "External id": 1422377,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10280 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.7", "pid": 2338710, "tid": 2379450, + "ts": 6410536012478.314, "dur": 733.302, + "args": { + "External id": 1422378,"Record function id": 0, "Ev Idx": 10281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410536012500.429, "dur": 695.695, + "args": { + "External id": 1422379,"Record function id": 0, "Ev Idx": 10282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536012577.801, "dur": 6.590, + "args": { + "External id": 1422380,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536012606.373, "dur": 34.490, + "args": { + "External id": 1422381,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012612.255, "dur": 1.976, + "args": { + "External id": 1422382,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012616.917, "dur": 3.451, + "args": { + "External id": 1422383,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012622.266, "dur": 0.572, + "args": { + "External id": 1422384,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012624.135, "dur": 0.681, + "args": { + "External id": 1422385,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012626.754, "dur": 0.848, + "args": { + "External id": 1422386,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012629.368, "dur": 0.820, + "args": { + "External id": 1422387,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012631.240, "dur": 0.672, + "args": { + "External id": 1422388,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012633.786, "dur": 0.487, + "args": { + "External id": 1422389,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012635.995, "dur": 0.503, + "args": { + "External id": 1422390,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536012660.855, "dur": 49.506, + "args": { + "External id": 1422391,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410536012746.001, "dur": 122.533, + "args": { + "External id": 1422392,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536012759.098, "dur": 6.748, + "args": { + "External id": 1422393,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410536012772.030, "dur": 12.392, + "args": { + "External id": 1422394,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410536012777.116, "dur": 6.816, + "args": { + "External id": 1422395,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012781.608, "dur": 0.829, + "args": { + "External id": 1422396,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536012792.502, "dur": 24.766, + "args": { + "External id": 1422397,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012794.572, "dur": 0.659, + "args": { + "External id": 1422398,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012797.030, "dur": 0.525, + "args": { + "External id": 1422399,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012799.271, "dur": 0.762, + "args": { + "External id": 1422400,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012801.904, "dur": 0.548, + "args": { + "External id": 1422401,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012804.175, "dur": 0.296, + "args": { + "External id": 1422402,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012805.482, "dur": 0.428, + "args": { + "External id": 1422403,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012807.588, "dur": 2.912, + "args": { + "External id": 1422404,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012812.262, "dur": 0.366, + "args": { + "External id": 1422405,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536012813.697, "dur": 0.487, + "args": { + "External id": 1422406,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536012828.445, "dur": 31.646, + "args": { + "External id": 1422407,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536012921.330, "dur": 178.439, + "args": { + "External id": 1422408,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536012951.082, "dur": 100.953, + "args": { + "External id": 1422409,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10312, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536012962.044, "dur": 84.958, + "args": { + "External id": 1422410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536013124.740, "dur": 3.549, + "args": { + "External id": 1422411,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10314, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536013230.673, "dur": 2074.200, + "args": { + "External id": 1422412,"Sequence number": 15109089, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10315 + } + }, + { + "ph": "f", "id": 430, "pid": 2338710, "tid": 2379450, "ts": 6410536013230.673, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536013361.596, "dur": 142.713, + "args": { + "External id": 1422413,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536013559.529, "dur": 47.528, + "args": { + "External id": 1422414,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536013630.104, "dur": 60.405, + "args": { + "External id": 1422415,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536013702.329, "dur": 36.335, + "args": { + "External id": 1422416,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536013745.552, "dur": 35.929, + "args": { + "External id": 1422417,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536013791.539, "dur": 31.194, + "args": { + "External id": 1422418,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536013830.874, "dur": 34.012, + "args": { + "External id": 1422419,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536013893.850, "dur": 24.992, + "args": { + "External id": 1422420,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536013941.147, "dur": 33.636, + "args": { + "External id": 1422421,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536014001.505, "dur": 21.965, + "args": { + "External id": 1422422,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536014036.924, "dur": 15.742, + "args": { + "External id": 1422423,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536014108.638, "dur": 53.512, + "args": { + "External id": 1422424,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536014167.454, "dur": 41.553, + "args": { + "External id": 1422425,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536014246.639, "dur": 346.432, + "args": { + "External id": 1422426,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536014346.309, "dur": 7.253, + "args": { + "External id": 1422427,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536014355.866, "dur": 5.302, + "args": { + "External id": 1422428,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536014362.646, "dur": 2.952, + "args": { + "External id": 1422429,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536014366.936, "dur": 2.635, + "args": { + "External id": 1422430,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536014454.979, "dur": 8.232, + "args": { + "External id": 1422431,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536014457.764, "dur": 4.315, + "args": { + "External id": 1422432,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536014465.718, "dur": 40.914, + "args": { + "External id": 1422433,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536014472.925, "dur": 2.457, + "args": { + "External id": 1422434,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536014508.382, "dur": 2.296, + "args": { + "External id": 1422435,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536014509.614, "dur": 0.919, + "args": { + "External id": 1422436,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536014511.657, "dur": 16.261, + "args": { + "External id": 1422437,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536014513.699, "dur": 0.558, + "args": { + "External id": 1422438,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536014641.514, "dur": 36.974, + "args": { + "External id": 1422439,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536014698.277, "dur": 18.968, + "args": { + "External id": 1422440,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536014730.342, "dur": 53.804, + "args": { + "External id": 1422441,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536014792.866, "dur": 46.753, + "args": { + "External id": 1422442,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536014851.808, "dur": 25.636, + "args": { + "External id": 1422443,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536014884.941, "dur": 36.406, + "args": { + "External id": 1422444,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536014930.418, "dur": 31.970, + "args": { + "External id": 1422445,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536014971.591, "dur": 36.858, + "args": { + "External id": 1422446,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536015030.068, "dur": 64.731, + "args": { + "External id": 1422447,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536015118.150, "dur": 32.285, + "args": { + "External id": 1422448,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536015167.506, "dur": 20.936, + "args": { + "External id": 1422449,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536015206.559, "dur": 19.742, + "args": { + "External id": 1422450,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536015249.146, "dur": 20.604, + "args": { + "External id": 1422451,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015358.648, "dur": 18.590, + "args": { + "External id": 1422452,"Record function id": 0, "Ev Idx": 10355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015363.029, "dur": 13.051, + "args": { + "External id": 1422453,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015368.060, "dur": 6.822, + "args": { + "External id": 1422454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015369.967, "dur": 4.737, + "args": { + "External id": 1422455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015382.042, "dur": 6.863, + "args": { + "External id": 1422456,"Record function id": 0, "Ev Idx": 10359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015383.698, "dur": 4.595, + "args": { + "External id": 1422457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015384.680, "dur": 2.922, + "args": { + "External id": 1422458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015385.633, "dur": 1.849, + "args": { + "External id": 1422459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015392.885, "dur": 9.702, + "args": { + "External id": 1422460,"Record function id": 0, "Ev Idx": 10363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015394.734, "dur": 7.313, + "args": { + "External id": 1422461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015398.849, "dur": 2.644, + "args": { + "External id": 1422462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015399.802, "dur": 1.582, + "args": { + "External id": 1422463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015406.474, "dur": 25.859, + "args": { + "External id": 1422464,"Record function id": 0, "Ev Idx": 10367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015408.034, "dur": 22.565, + "args": { + "External id": 1422465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015408.778, "dur": 4.735, + "args": { + "External id": 1422466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015409.815, "dur": 3.583, + "args": { + "External id": 1422467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015439.051, "dur": 7.801, + "args": { + "External id": 1422468,"Record function id": 0, "Ev Idx": 10371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015441.332, "dur": 5.005, + "args": { + "External id": 1422469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015442.566, "dur": 3.020, + "args": { + "External id": 1422470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015443.634, "dur": 1.834, + "args": { + "External id": 1422471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015450.894, "dur": 8.851, + "args": { + "External id": 1422472,"Record function id": 0, "Ev Idx": 10375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015452.392, "dur": 6.788, + "args": { + "External id": 1422473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015453.051, "dur": 5.602, + "args": { + "External id": 1422474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015457.478, "dur": 1.069, + "args": { + "External id": 1422475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015463.742, "dur": 4.999, + "args": { + "External id": 1422476,"Record function id": 0, "Ev Idx": 10379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015465.261, "dur": 2.926, + "args": { + "External id": 1422477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015466.091, "dur": 1.529, + "args": { + "External id": 1422478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015466.791, "dur": 0.705, + "args": { + "External id": 1422479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015472.379, "dur": 4.721, + "args": { + "External id": 1422480,"Record function id": 0, "Ev Idx": 10383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015473.800, "dur": 2.752, + "args": { + "External id": 1422481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015474.480, "dur": 1.385, + "args": { + "External id": 1422482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015474.873, "dur": 0.905, + "args": { + "External id": 1422483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015481.218, "dur": 4.283, + "args": { + "External id": 1422484,"Record function id": 0, "Ev Idx": 10387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536015482.467, "dur": 2.494, + "args": { + "External id": 1422485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015483.360, "dur": 1.108, + "args": { + "External id": 1422486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536015483.687, "dur": 0.693, + "args": { + "External id": 1422487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536015490.186, "dur": 67379.888, + "args": { + "External id": 1422488,"Record function id": 0, "Sequence number": 15109088, "Fwd thread id": 1, "Ev Idx": 10391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536015491.758, "dur": 67367.302, + "args": { + "External id": 1422489,"Sequence number": 15109088, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10392 + } + }, + { + "ph": "f", "id": 431, "pid": 2338710, "tid": 2379450, "ts": 6410536015491.758, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410536015527.128, "dur": 45.424, + "args": { + "External id": 1422490,"Record function id": 0, "Ev Idx": 10393 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410536015581.522, "dur": 73.267, + "args": { + "External id": 1422491,"Record function id": 0, "Ev Idx": 10394 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 2338710, "tid": 2379450, + "ts": 6410536015662.294, "dur": 67187.838, + "args": { + "External id": 1422492,"Record function id": 0, "Ev Idx": 10395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536015770.172, "dur": 7.976, + "args": { + "External id": 1422493,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536015789.879, "dur": 5.448, + "args": { + "External id": 1422494,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536015811.167, "dur": 65917.768, + "args": { + "External id": 1422495,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536015827.209, "dur": 65886.161, + "args": { + "External id": 1422496,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536015949.589, "dur": 20.356, + "args": { + "External id": 1422497,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536015993.015, "dur": 65665.514, + "args": { + "External id": 1422498,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536015996.067, "dur": 65661.232, + "args": { + "External id": 1422499,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536016001.681, "dur": 13.046, + "args": { + "External id": 1422500,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536016019.933, "dur": 65631.689, + "args": { + "External id": 1422501,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536081854.970, "dur": 14.551, + "args": { + "External id": 1422502,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536081859.045, "dur": 10.021, + "args": { + "External id": 1422503,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536081906.621, "dur": 479.066, + "args": { + "External id": 1422504,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536081940.816, "dur": 438.526, + "args": { + "External id": 1422505,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10408, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536081958.501, "dur": 413.288, + "args": { + "External id": 1422506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536082428.419, "dur": 4.022, + "args": { + "External id": 1422507,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10410, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082508.237, "dur": 8.115, + "args": { + "External id": 1422508,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082532.371, "dur": 41.864, + "args": { + "External id": 1422509,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082586.899, "dur": 2.276, + "args": { + "External id": 1422510,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082595.824, "dur": 14.380, + "args": { + "External id": 1422511,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082616.978, "dur": 1.246, + "args": { + "External id": 1422512,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082623.958, "dur": 12.239, + "args": { + "External id": 1422513,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082642.664, "dur": 1.184, + "args": { + "External id": 1422514,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082648.718, "dur": 12.661, + "args": { + "External id": 1422515,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082666.731, "dur": 1.020, + "args": { + "External id": 1422516,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082672.215, "dur": 10.814, + "args": { + "External id": 1422517,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082687.555, "dur": 1.357, + "args": { + "External id": 1422518,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082693.382, "dur": 13.938, + "args": { + "External id": 1422519,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082712.097, "dur": 3.803, + "args": { + "External id": 1422520,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082720.459, "dur": 12.159, + "args": { + "External id": 1422521,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082739.841, "dur": 1.031, + "args": { + "External id": 1422522,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082745.478, "dur": 13.587, + "args": { + "External id": 1422523,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536082763.825, "dur": 1.164, + "args": { + "External id": 1422524,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536082769.565, "dur": 12.118, + "args": { + "External id": 1422525,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536082888.975, "dur": 3459.955, + "args": { + "External id": 1422526,"Record function id": 0, "Ev Idx": 10429 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410536082913.591, "dur": 1299.607, + "args": { + "External id": 1422527,"Record function id": 0, "Ev Idx": 10430 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410536082932.136, "dur": 429.191, + "args": { + "External id": 1422528,"Record function id": 0, "Ev Idx": 10431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083030.106, "dur": 4.391, + "args": { + "External id": 1422529,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083038.559, "dur": 1.172, + "args": { + "External id": 1422530,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083041.735, "dur": 0.994, + "args": { + "External id": 1422531,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083044.734, "dur": 1.183, + "args": { + "External id": 1422532,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083047.799, "dur": 1.154, + "args": { + "External id": 1422533,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083053.701, "dur": 54.179, + "args": { + "External id": 1422534,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083113.518, "dur": 1.319, + "args": { + "External id": 1422535,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083116.747, "dur": 2.391, + "args": { + "External id": 1422536,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083121.189, "dur": 0.970, + "args": { + "External id": 1422537,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536083126.170, "dur": 0.896, + "args": { + "External id": 1422538,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536083149.133, "dur": 172.675, + "args": { + "External id": 1422539,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536083169.300, "dur": 146.455, + "args": { + "External id": 1422540,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536083187.191, "dur": 15.821, + "args": { + "External id": 1422541,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536083207.435, "dur": 76.582, + "args": { + "External id": 1422542,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536083210.575, "dur": 72.939, + "args": { + "External id": 1422543,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083215.351, "dur": 7.218, + "args": { + "External id": 1422544,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536083224.659, "dur": 58.134, + "args": { + "External id": 1422545,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10448 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.6", "pid": 2338710, "tid": 2379450, + "ts": 6410536083487.320, "dur": 716.374, + "args": { + "External id": 1422546,"Record function id": 0, "Ev Idx": 10449 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410536083508.660, "dur": 680.044, + "args": { + "External id": 1422547,"Record function id": 0, "Ev Idx": 10450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536083588.018, "dur": 7.520, + "args": { + "External id": 1422548,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536083612.951, "dur": 39.102, + "args": { + "External id": 1422549,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083619.559, "dur": 4.127, + "args": { + "External id": 1422550,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083625.715, "dur": 0.799, + "args": { + "External id": 1422551,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083628.448, "dur": 0.536, + "args": { + "External id": 1422552,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083630.803, "dur": 0.418, + "args": { + "External id": 1422553,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083632.408, "dur": 0.641, + "args": { + "External id": 1422554,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083634.844, "dur": 0.500, + "args": { + "External id": 1422555,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083640.639, "dur": 0.382, + "args": { + "External id": 1422556,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083642.357, "dur": 0.601, + "args": { + "External id": 1422557,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083644.702, "dur": 2.640, + "args": { + "External id": 1422558,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536083664.215, "dur": 54.354, + "args": { + "External id": 1422559,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410536083756.841, "dur": 120.742, + "args": { + "External id": 1422560,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536083769.498, "dur": 3.740, + "args": { + "External id": 1422561,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410536083779.767, "dur": 11.824, + "args": { + "External id": 1422562,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410536083784.755, "dur": 6.370, + "args": { + "External id": 1422563,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083788.909, "dur": 0.737, + "args": { + "External id": 1422564,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536083799.454, "dur": 25.881, + "args": { + "External id": 1422565,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083801.877, "dur": 0.717, + "args": { + "External id": 1422566,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083803.993, "dur": 0.454, + "args": { + "External id": 1422567,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083806.380, "dur": 0.432, + "args": { + "External id": 1422568,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083808.909, "dur": 0.773, + "args": { + "External id": 1422569,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083810.830, "dur": 0.620, + "args": { + "External id": 1422570,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083813.213, "dur": 2.587, + "args": { + "External id": 1422571,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083817.487, "dur": 0.377, + "args": { + "External id": 1422572,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083819.036, "dur": 0.919, + "args": { + "External id": 1422573,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536083821.567, "dur": 0.477, + "args": { + "External id": 1422574,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536083837.039, "dur": 31.968, + "args": { + "External id": 1422575,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536083927.935, "dur": 169.551, + "args": { + "External id": 1422576,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536083953.650, "dur": 98.724, + "args": { + "External id": 1422577,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10480, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536083964.342, "dur": 83.219, + "args": { + "External id": 1422578,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536084120.900, "dur": 3.424, + "args": { + "External id": 1422579,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10482, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536084222.530, "dur": 2100.415, + "args": { + "External id": 1422580,"Sequence number": 15109087, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10483 + } + }, + { + "ph": "f", "id": 432, "pid": 2338710, "tid": 2379450, "ts": 6410536084222.530, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536084352.568, "dur": 142.338, + "args": { + "External id": 1422581,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536084552.262, "dur": 48.296, + "args": { + "External id": 1422582,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536084622.110, "dur": 64.472, + "args": { + "External id": 1422583,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536084697.696, "dur": 37.556, + "args": { + "External id": 1422584,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536084742.918, "dur": 35.381, + "args": { + "External id": 1422585,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536084787.654, "dur": 32.556, + "args": { + "External id": 1422586,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536084828.222, "dur": 32.897, + "args": { + "External id": 1422587,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536084891.191, "dur": 27.903, + "args": { + "External id": 1422588,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536084941.986, "dur": 32.387, + "args": { + "External id": 1422589,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536085000.210, "dur": 22.514, + "args": { + "External id": 1422590,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536085041.464, "dur": 59.261, + "args": { + "External id": 1422591,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536085120.132, "dur": 53.601, + "args": { + "External id": 1422592,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536085178.858, "dur": 38.549, + "args": { + "External id": 1422593,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536085251.149, "dur": 343.565, + "args": { + "External id": 1422594,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536085364.663, "dur": 10.477, + "args": { + "External id": 1422595,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536085378.056, "dur": 3.148, + "args": { + "External id": 1422596,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536085382.937, "dur": 2.359, + "args": { + "External id": 1422597,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536085386.801, "dur": 2.393, + "args": { + "External id": 1422598,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536085467.244, "dur": 6.643, + "args": { + "External id": 1422599,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536085469.247, "dur": 4.209, + "args": { + "External id": 1422600,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536085476.392, "dur": 42.408, + "args": { + "External id": 1422601,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536085482.942, "dur": 5.389, + "args": { + "External id": 1422602,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536085520.564, "dur": 2.208, + "args": { + "External id": 1422603,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536085521.969, "dur": 0.700, + "args": { + "External id": 1422604,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536085523.551, "dur": 17.508, + "args": { + "External id": 1422605,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536085525.805, "dur": 0.856, + "args": { + "External id": 1422606,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536085639.926, "dur": 41.449, + "args": { + "External id": 1422607,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536085702.149, "dur": 22.870, + "args": { + "External id": 1422608,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536085735.580, "dur": 58.377, + "args": { + "External id": 1422609,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536085805.350, "dur": 45.838, + "args": { + "External id": 1422610,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536085865.368, "dur": 25.970, + "args": { + "External id": 1422611,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536085899.030, "dur": 41.266, + "args": { + "External id": 1422612,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536085949.475, "dur": 34.272, + "args": { + "External id": 1422613,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536085992.183, "dur": 35.134, + "args": { + "External id": 1422614,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536086051.297, "dur": 74.100, + "args": { + "External id": 1422615,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536086149.696, "dur": 30.809, + "args": { + "External id": 1422616,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536086198.515, "dur": 20.728, + "args": { + "External id": 1422617,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536086238.649, "dur": 15.943, + "args": { + "External id": 1422618,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536086269.397, "dur": 17.655, + "args": { + "External id": 1422619,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086374.960, "dur": 18.832, + "args": { + "External id": 1422620,"Record function id": 0, "Ev Idx": 10523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086379.236, "dur": 13.181, + "args": { + "External id": 1422621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086384.495, "dur": 6.812, + "args": { + "External id": 1422622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086386.445, "dur": 4.675, + "args": { + "External id": 1422623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086398.902, "dur": 8.423, + "args": { + "External id": 1422624,"Record function id": 0, "Ev Idx": 10527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086400.630, "dur": 6.130, + "args": { + "External id": 1422625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086401.549, "dur": 4.639, + "args": { + "External id": 1422626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086402.402, "dur": 3.622, + "args": { + "External id": 1422627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086411.174, "dur": 27.826, + "args": { + "External id": 1422628,"Record function id": 0, "Ev Idx": 10531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086413.040, "dur": 24.648, + "args": { + "External id": 1422629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086432.108, "dur": 4.372, + "args": { + "External id": 1422630,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086433.999, "dur": 2.167, + "args": { + "External id": 1422631,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086445.256, "dur": 6.646, + "args": { + "External id": 1422632,"Record function id": 0, "Ev Idx": 10535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086447.289, "dur": 4.121, + "args": { + "External id": 1422633,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086448.610, "dur": 2.305, + "args": { + "External id": 1422634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086449.552, "dur": 1.233, + "args": { + "External id": 1422635,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086455.621, "dur": 7.447, + "args": { + "External id": 1422636,"Record function id": 0, "Ev Idx": 10539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086458.111, "dur": 4.442, + "args": { + "External id": 1422637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086458.712, "dur": 3.217, + "args": { + "External id": 1422638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086460.020, "dur": 1.815, + "args": { + "External id": 1422639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086466.738, "dur": 6.605, + "args": { + "External id": 1422640,"Record function id": 0, "Ev Idx": 10543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086468.705, "dur": 4.168, + "args": { + "External id": 1422641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086469.606, "dur": 2.746, + "args": { + "External id": 1422642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086470.951, "dur": 1.268, + "args": { + "External id": 1422643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086477.119, "dur": 5.266, + "args": { + "External id": 1422644,"Record function id": 0, "Ev Idx": 10547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086478.405, "dur": 3.504, + "args": { + "External id": 1422645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086478.966, "dur": 2.456, + "args": { + "External id": 1422646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086480.115, "dur": 1.214, + "args": { + "External id": 1422647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086486.058, "dur": 6.534, + "args": { + "External id": 1422648,"Record function id": 0, "Ev Idx": 10551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086487.942, "dur": 4.163, + "args": { + "External id": 1422649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086488.581, "dur": 2.734, + "args": { + "External id": 1422650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086489.865, "dur": 1.355, + "args": { + "External id": 1422651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086496.895, "dur": 8.704, + "args": { + "External id": 1422652,"Record function id": 0, "Ev Idx": 10555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536086498.490, "dur": 6.630, + "args": { + "External id": 1422653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086499.058, "dur": 5.400, + "args": { + "External id": 1422654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536086500.147, "dur": 4.207, + "args": { + "External id": 1422655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536086510.540, "dur": 65176.071, + "args": { + "External id": 1422656,"Record function id": 0, "Sequence number": 15109086, "Fwd thread id": 1, "Ev Idx": 10559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536086512.380, "dur": 65163.195, + "args": { + "External id": 1422657,"Sequence number": 15109086, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10560 + } + }, + { + "ph": "f", "id": 433, "pid": 2338710, "tid": 2379450, "ts": 6410536086512.380, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410536086548.890, "dur": 47.185, + "args": { + "External id": 1422658,"Record function id": 0, "Ev Idx": 10561 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410536086606.414, "dur": 74.119, + "args": { + "External id": 1422659,"Record function id": 0, "Ev Idx": 10562 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 2338710, "tid": 2379450, + "ts": 6410536086687.809, "dur": 64979.080, + "args": { + "External id": 1422660,"Record function id": 0, "Ev Idx": 10563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536086800.530, "dur": 8.041, + "args": { + "External id": 1422661,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536086820.232, "dur": 8.957, + "args": { + "External id": 1422662,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536086845.421, "dur": 63629.320, + "args": { + "External id": 1422663,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536086862.105, "dur": 63598.258, + "args": { + "External id": 1422664,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536087006.816, "dur": 25.920, + "args": { + "External id": 1422665,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536087103.793, "dur": 63288.376, + "args": { + "External id": 1422666,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536087107.460, "dur": 63283.457, + "args": { + "External id": 1422667,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536087113.193, "dur": 14.805, + "args": { + "External id": 1422668,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536087130.696, "dur": 63254.082, + "args": { + "External id": 1422669,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536150600.076, "dur": 15.717, + "args": { + "External id": 1422670,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536150604.166, "dur": 10.941, + "args": { + "External id": 1422671,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536150652.818, "dur": 532.425, + "args": { + "External id": 1422672,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536150693.448, "dur": 485.122, + "args": { + "External id": 1422673,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10576, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536150706.937, "dur": 464.157, + "args": { + "External id": 1422674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536151214.619, "dur": 2.893, + "args": { + "External id": 1422675,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10578, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151295.168, "dur": 7.950, + "args": { + "External id": 1422676,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151318.901, "dur": 43.031, + "args": { + "External id": 1422677,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151374.418, "dur": 2.074, + "args": { + "External id": 1422678,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151383.712, "dur": 16.435, + "args": { + "External id": 1422679,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151407.463, "dur": 1.218, + "args": { + "External id": 1422680,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151429.511, "dur": 17.370, + "args": { + "External id": 1422681,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151455.956, "dur": 4.012, + "args": { + "External id": 1422682,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151464.737, "dur": 14.155, + "args": { + "External id": 1422683,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151484.097, "dur": 1.009, + "args": { + "External id": 1422684,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151489.797, "dur": 13.122, + "args": { + "External id": 1422685,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151507.631, "dur": 1.110, + "args": { + "External id": 1422686,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151513.346, "dur": 13.764, + "args": { + "External id": 1422687,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151532.320, "dur": 1.227, + "args": { + "External id": 1422688,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151538.137, "dur": 11.702, + "args": { + "External id": 1422689,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151554.757, "dur": 1.403, + "args": { + "External id": 1422690,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151560.622, "dur": 11.418, + "args": { + "External id": 1422691,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151579.107, "dur": 1.120, + "args": { + "External id": 1422692,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151584.626, "dur": 11.258, + "args": { + "External id": 1422693,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536151705.446, "dur": 3453.780, + "args": { + "External id": 1422694,"Record function id": 0, "Ev Idx": 10597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410536151728.554, "dur": 1244.697, + "args": { + "External id": 1422695,"Record function id": 0, "Ev Idx": 10598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410536151746.361, "dur": 420.300, + "args": { + "External id": 1422696,"Record function id": 0, "Ev Idx": 10599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151849.447, "dur": 5.033, + "args": { + "External id": 1422697,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151858.041, "dur": 0.926, + "args": { + "External id": 1422698,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151861.558, "dur": 3.583, + "args": { + "External id": 1422699,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151867.112, "dur": 1.115, + "args": { + "External id": 1422700,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151869.816, "dur": 1.111, + "args": { + "External id": 1422701,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151872.686, "dur": 0.998, + "args": { + "External id": 1422702,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151877.807, "dur": 1.323, + "args": { + "External id": 1422703,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151880.757, "dur": 2.335, + "args": { + "External id": 1422704,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151885.247, "dur": 1.033, + "args": { + "External id": 1422705,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536151887.888, "dur": 0.933, + "args": { + "External id": 1422706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536151911.177, "dur": 214.404, + "args": { + "External id": 1422707,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536151929.506, "dur": 188.784, + "args": { + "External id": 1422708,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536151945.997, "dur": 18.251, + "args": { + "External id": 1422709,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536151968.714, "dur": 74.289, + "args": { + "External id": 1422710,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536151972.046, "dur": 70.525, + "args": { + "External id": 1422711,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536151976.403, "dur": 7.406, + "args": { + "External id": 1422712,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536151985.672, "dur": 56.037, + "args": { + "External id": 1422713,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.5", "pid": 2338710, "tid": 2379450, + "ts": 6410536152275.808, "dur": 688.567, + "args": { + "External id": 1422714,"Record function id": 0, "Ev Idx": 10617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410536152296.483, "dur": 653.540, + "args": { + "External id": 1422715,"Record function id": 0, "Ev Idx": 10618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536152372.583, "dur": 6.775, + "args": { + "External id": 1422716,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536152396.636, "dur": 51.920, + "args": { + "External id": 1422717,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152402.345, "dur": 2.155, + "args": { + "External id": 1422718,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152406.858, "dur": 0.636, + "args": { + "External id": 1422719,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152409.861, "dur": 0.700, + "args": { + "External id": 1422720,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152411.681, "dur": 0.792, + "args": { + "External id": 1422721,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152431.072, "dur": 1.086, + "args": { + "External id": 1422722,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152434.694, "dur": 2.788, + "args": { + "External id": 1422723,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152438.708, "dur": 0.540, + "args": { + "External id": 1422724,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152441.205, "dur": 0.429, + "args": { + "External id": 1422725,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152443.313, "dur": 0.577, + "args": { + "External id": 1422726,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536152462.952, "dur": 50.776, + "args": { + "External id": 1422727,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410536152552.045, "dur": 122.465, + "args": { + "External id": 1422728,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536152564.961, "dur": 5.487, + "args": { + "External id": 1422729,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410536152576.715, "dur": 11.897, + "args": { + "External id": 1422730,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410536152581.824, "dur": 6.285, + "args": { + "External id": 1422731,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152585.518, "dur": 0.983, + "args": { + "External id": 1422732,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536152596.521, "dur": 25.342, + "args": { + "External id": 1422733,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152598.719, "dur": 0.596, + "args": { + "External id": 1422734,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152601.367, "dur": 0.322, + "args": { + "External id": 1422735,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152603.196, "dur": 3.009, + "args": { + "External id": 1422736,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152607.946, "dur": 0.453, + "args": { + "External id": 1422737,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152610.400, "dur": 0.370, + "args": { + "External id": 1422738,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152611.815, "dur": 0.432, + "args": { + "External id": 1422739,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152613.864, "dur": 0.397, + "args": { + "External id": 1422740,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152616.100, "dur": 0.462, + "args": { + "External id": 1422741,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536152617.839, "dur": 0.743, + "args": { + "External id": 1422742,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536152633.584, "dur": 32.418, + "args": { + "External id": 1422743,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536152727.978, "dur": 140.392, + "args": { + "External id": 1422744,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536152766.182, "dur": 98.203, + "args": { + "External id": 1422745,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10648, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536152777.583, "dur": 81.972, + "args": { + "External id": 1422746,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536152887.108, "dur": 2.045, + "args": { + "External id": 1422747,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10650, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536152980.957, "dur": 2152.010, + "args": { + "External id": 1422748,"Sequence number": 15109085, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10651 + } + }, + { + "ph": "f", "id": 434, "pid": 2338710, "tid": 2379450, "ts": 6410536152980.957, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536153156.830, "dur": 127.116, + "args": { + "External id": 1422749,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536153336.430, "dur": 49.300, + "args": { + "External id": 1422750,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536153406.552, "dur": 81.231, + "args": { + "External id": 1422751,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536153506.257, "dur": 38.805, + "args": { + "External id": 1422752,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536153552.054, "dur": 37.536, + "args": { + "External id": 1422753,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536153598.135, "dur": 32.232, + "args": { + "External id": 1422754,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536153638.057, "dur": 33.629, + "args": { + "External id": 1422755,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536153705.925, "dur": 29.896, + "args": { + "External id": 1422756,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536153759.556, "dur": 32.056, + "args": { + "External id": 1422757,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536153820.665, "dur": 23.217, + "args": { + "External id": 1422758,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536153863.600, "dur": 17.550, + "args": { + "External id": 1422759,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536153891.483, "dur": 48.392, + "args": { + "External id": 1422760,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536153944.554, "dur": 37.788, + "args": { + "External id": 1422761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536154016.114, "dur": 373.448, + "args": { + "External id": 1422762,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536154157.845, "dur": 8.472, + "args": { + "External id": 1422763,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536154169.212, "dur": 3.048, + "args": { + "External id": 1422764,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536154173.956, "dur": 2.569, + "args": { + "External id": 1422765,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536154177.917, "dur": 2.594, + "args": { + "External id": 1422766,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536154249.930, "dur": 6.510, + "args": { + "External id": 1422767,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536154251.935, "dur": 3.919, + "args": { + "External id": 1422768,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536154258.707, "dur": 41.080, + "args": { + "External id": 1422769,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536154265.430, "dur": 3.929, + "args": { + "External id": 1422770,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536154301.452, "dur": 1.980, + "args": { + "External id": 1422771,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536154302.536, "dur": 0.777, + "args": { + "External id": 1422772,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536154304.993, "dur": 22.936, + "args": { + "External id": 1422773,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536154307.812, "dur": 0.647, + "args": { + "External id": 1422774,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536154453.086, "dur": 40.643, + "args": { + "External id": 1422775,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536154515.532, "dur": 19.748, + "args": { + "External id": 1422776,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536154547.467, "dur": 69.456, + "args": { + "External id": 1422777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536154625.920, "dur": 49.633, + "args": { + "External id": 1422778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536154688.319, "dur": 26.687, + "args": { + "External id": 1422779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536154723.274, "dur": 36.460, + "args": { + "External id": 1422780,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536154769.078, "dur": 33.241, + "args": { + "External id": 1422781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536154811.100, "dur": 35.818, + "args": { + "External id": 1422782,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536154868.123, "dur": 29.916, + "args": { + "External id": 1422783,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536154917.008, "dur": 29.706, + "args": { + "External id": 1422784,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536154964.660, "dur": 21.914, + "args": { + "External id": 1422785,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536155002.525, "dur": 18.325, + "args": { + "External id": 1422786,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536155035.438, "dur": 19.809, + "args": { + "External id": 1422787,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155185.542, "dur": 18.256, + "args": { + "External id": 1422788,"Record function id": 0, "Ev Idx": 10691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155189.865, "dur": 12.708, + "args": { + "External id": 1422789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155195.007, "dur": 6.453, + "args": { + "External id": 1422790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155196.905, "dur": 4.369, + "args": { + "External id": 1422791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155208.363, "dur": 6.818, + "args": { + "External id": 1422792,"Record function id": 0, "Ev Idx": 10695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155210.313, "dur": 4.280, + "args": { + "External id": 1422793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155211.179, "dur": 2.881, + "args": { + "External id": 1422794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155212.473, "dur": 1.463, + "args": { + "External id": 1422795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155218.919, "dur": 6.039, + "args": { + "External id": 1422796,"Record function id": 0, "Ev Idx": 10699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155220.360, "dur": 4.090, + "args": { + "External id": 1422797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155220.917, "dur": 2.743, + "args": { + "External id": 1422798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155222.253, "dur": 1.289, + "args": { + "External id": 1422799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155228.613, "dur": 5.694, + "args": { + "External id": 1422800,"Record function id": 0, "Ev Idx": 10703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155230.413, "dur": 3.413, + "args": { + "External id": 1422801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155230.958, "dur": 2.254, + "args": { + "External id": 1422802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155231.927, "dur": 1.187, + "args": { + "External id": 1422803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155237.962, "dur": 5.448, + "args": { + "External id": 1422804,"Record function id": 0, "Ev Idx": 10707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155239.551, "dur": 3.358, + "args": { + "External id": 1422805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155240.074, "dur": 2.109, + "args": { + "External id": 1422806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155240.782, "dur": 1.305, + "args": { + "External id": 1422807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155247.373, "dur": 7.494, + "args": { + "External id": 1422808,"Record function id": 0, "Ev Idx": 10711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155248.608, "dur": 5.752, + "args": { + "External id": 1422809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155249.133, "dur": 4.598, + "args": { + "External id": 1422810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155250.024, "dur": 3.595, + "args": { + "External id": 1422811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155258.589, "dur": 5.167, + "args": { + "External id": 1422812,"Record function id": 0, "Ev Idx": 10715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155259.950, "dur": 3.263, + "args": { + "External id": 1422813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155260.762, "dur": 1.968, + "args": { + "External id": 1422814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155261.559, "dur": 1.058, + "args": { + "External id": 1422815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155268.026, "dur": 4.914, + "args": { + "External id": 1422816,"Record function id": 0, "Ev Idx": 10719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155269.536, "dur": 2.909, + "args": { + "External id": 1422817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155270.139, "dur": 1.832, + "args": { + "External id": 1422818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155270.720, "dur": 1.116, + "args": { + "External id": 1422819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155276.963, "dur": 4.529, + "args": { + "External id": 1422820,"Record function id": 0, "Ev Idx": 10723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536155278.289, "dur": 2.718, + "args": { + "External id": 1422821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155278.867, "dur": 1.632, + "args": { + "External id": 1422822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536155279.415, "dur": 0.996, + "args": { + "External id": 1422823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536155286.119, "dur": 68914.263, + "args": { + "External id": 1422824,"Record function id": 0, "Sequence number": 15109084, "Fwd thread id": 1, "Ev Idx": 10727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536155287.581, "dur": 68901.700, + "args": { + "External id": 1422825,"Sequence number": 15109084, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10728 + } + }, + { + "ph": "f", "id": 435, "pid": 2338710, "tid": 2379450, "ts": 6410536155287.581, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410536155322.643, "dur": 45.160, + "args": { + "External id": 1422826,"Record function id": 0, "Ev Idx": 10729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410536155377.176, "dur": 100.957, + "args": { + "External id": 1422827,"Record function id": 0, "Ev Idx": 10730 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 2338710, "tid": 2379450, + "ts": 6410536155489.828, "dur": 68689.675, + "args": { + "External id": 1422828,"Record function id": 0, "Ev Idx": 10731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536155596.782, "dur": 8.700, + "args": { + "External id": 1422829,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536155617.582, "dur": 5.656, + "args": { + "External id": 1422830,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536155639.887, "dur": 67393.064, + "args": { + "External id": 1422831,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536155656.377, "dur": 67361.778, + "args": { + "External id": 1422832,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536155788.688, "dur": 21.684, + "args": { + "External id": 1422833,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536155833.769, "dur": 67127.954, + "args": { + "External id": 1422834,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536155839.670, "dur": 67120.743, + "args": { + "External id": 1422835,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536155845.155, "dur": 10.469, + "args": { + "External id": 1422836,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536155858.233, "dur": 67096.359, + "args": { + "External id": 1422837,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536223188.603, "dur": 14.923, + "args": { + "External id": 1422838,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536223192.599, "dur": 10.159, + "args": { + "External id": 1422839,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536223241.585, "dur": 372.222, + "args": { + "External id": 1422840,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536223278.133, "dur": 329.431, + "args": { + "External id": 1422841,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10744, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536223292.133, "dur": 308.515, + "args": { + "External id": 1422842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536223639.375, "dur": 2.636, + "args": { + "External id": 1422843,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10746, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536223710.612, "dur": 9.834, + "args": { + "External id": 1422844,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536223735.500, "dur": 40.301, + "args": { + "External id": 1422845,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536223791.598, "dur": 2.392, + "args": { + "External id": 1422846,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536223802.250, "dur": 18.623, + "args": { + "External id": 1422847,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536223830.977, "dur": 1.442, + "args": { + "External id": 1422848,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536223867.891, "dur": 21.757, + "args": { + "External id": 1422849,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536223904.990, "dur": 1.604, + "args": { + "External id": 1422850,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536223913.054, "dur": 18.958, + "args": { + "External id": 1422851,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536223939.120, "dur": 1.375, + "args": { + "External id": 1422852,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536223946.908, "dur": 13.950, + "args": { + "External id": 1422853,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536223965.951, "dur": 1.541, + "args": { + "External id": 1422854,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536223972.214, "dur": 15.039, + "args": { + "External id": 1422855,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536223991.921, "dur": 1.115, + "args": { + "External id": 1422856,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536223997.514, "dur": 12.078, + "args": { + "External id": 1422857,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224016.340, "dur": 1.040, + "args": { + "External id": 1422858,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536224021.595, "dur": 15.210, + "args": { + "External id": 1422859,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224041.986, "dur": 2.934, + "args": { + "External id": 1422860,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536224049.114, "dur": 49.482, + "args": { + "External id": 1422861,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536224220.707, "dur": 3432.359, + "args": { + "External id": 1422862,"Record function id": 0, "Ev Idx": 10765 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410536224244.854, "dur": 1280.373, + "args": { + "External id": 1422863,"Record function id": 0, "Ev Idx": 10766 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410536224266.303, "dur": 400.792, + "args": { + "External id": 1422864,"Record function id": 0, "Ev Idx": 10767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224373.130, "dur": 5.515, + "args": { + "External id": 1422865,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224382.153, "dur": 1.132, + "args": { + "External id": 1422866,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224385.755, "dur": 1.060, + "args": { + "External id": 1422867,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224388.587, "dur": 1.108, + "args": { + "External id": 1422868,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224392.175, "dur": 1.051, + "args": { + "External id": 1422869,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224395.025, "dur": 1.320, + "args": { + "External id": 1422870,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224400.071, "dur": 0.727, + "args": { + "External id": 1422871,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224403.380, "dur": 4.738, + "args": { + "External id": 1422872,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224410.040, "dur": 0.813, + "args": { + "External id": 1422873,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536224412.304, "dur": 0.931, + "args": { + "External id": 1422874,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536224454.870, "dur": 174.168, + "args": { + "External id": 1422875,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536224474.882, "dur": 148.319, + "args": { + "External id": 1422876,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536224491.836, "dur": 16.759, + "args": { + "External id": 1422877,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536224512.895, "dur": 79.123, + "args": { + "External id": 1422878,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536224517.748, "dur": 73.915, + "args": { + "External id": 1422879,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224522.700, "dur": 7.972, + "args": { + "External id": 1422880,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536224532.696, "dur": 58.283, + "args": { + "External id": 1422881,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.4", "pid": 2338710, "tid": 2379450, + "ts": 6410536224767.923, "dur": 748.973, + "args": { + "External id": 1422882,"Record function id": 0, "Ev Idx": 10785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410536224788.463, "dur": 711.625, + "args": { + "External id": 1422883,"Record function id": 0, "Ev Idx": 10786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536224860.480, "dur": 6.112, + "args": { + "External id": 1422884,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536224883.811, "dur": 30.646, + "args": { + "External id": 1422885,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224888.963, "dur": 1.909, + "args": { + "External id": 1422886,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224893.343, "dur": 0.504, + "args": { + "External id": 1422887,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224895.540, "dur": 3.108, + "args": { + "External id": 1422888,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224899.830, "dur": 0.822, + "args": { + "External id": 1422889,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224902.358, "dur": 0.416, + "args": { + "External id": 1422890,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224904.604, "dur": 0.302, + "args": { + "External id": 1422891,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224905.905, "dur": 0.397, + "args": { + "External id": 1422892,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224907.748, "dur": 0.492, + "args": { + "External id": 1422893,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536224910.056, "dur": 0.374, + "args": { + "External id": 1422894,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536224926.933, "dur": 50.346, + "args": { + "External id": 1422895,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410536225013.112, "dur": 188.836, + "args": { + "External id": 1422896,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536225024.470, "dur": 3.650, + "args": { + "External id": 1422897,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410536225034.563, "dur": 14.747, + "args": { + "External id": 1422898,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410536225039.415, "dur": 9.415, + "args": { + "External id": 1422899,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225044.053, "dur": 3.230, + "args": { + "External id": 1422900,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536225113.230, "dur": 27.216, + "args": { + "External id": 1422901,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225116.092, "dur": 0.913, + "args": { + "External id": 1422902,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225119.273, "dur": 0.524, + "args": { + "External id": 1422903,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225121.303, "dur": 0.658, + "args": { + "External id": 1422904,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225123.777, "dur": 0.484, + "args": { + "External id": 1422905,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225125.986, "dur": 0.435, + "args": { + "External id": 1422906,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225127.454, "dur": 0.502, + "args": { + "External id": 1422907,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225129.583, "dur": 0.409, + "args": { + "External id": 1422908,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225131.760, "dur": 2.747, + "args": { + "External id": 1422909,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536225135.922, "dur": 0.488, + "args": { + "External id": 1422910,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536225155.143, "dur": 37.282, + "args": { + "External id": 1422911,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536225260.116, "dur": 134.003, + "args": { + "External id": 1422912,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536225290.157, "dur": 99.447, + "args": { + "External id": 1422913,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10816, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536225301.519, "dur": 82.758, + "args": { + "External id": 1422914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536225412.147, "dur": 18.864, + "args": { + "External id": 1422915,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10818, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536225534.251, "dur": 2089.582, + "args": { + "External id": 1422916,"Sequence number": 15109083, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10819 + } + }, + { + "ph": "f", "id": 436, "pid": 2338710, "tid": 2379450, "ts": 6410536225534.251, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536225667.458, "dur": 127.364, + "args": { + "External id": 1422917,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536225842.373, "dur": 46.038, + "args": { + "External id": 1422918,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536225911.264, "dur": 54.735, + "args": { + "External id": 1422919,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536225978.012, "dur": 36.194, + "args": { + "External id": 1422920,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536226021.745, "dur": 80.752, + "args": { + "External id": 1422921,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536226117.132, "dur": 38.748, + "args": { + "External id": 1422922,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536226171.191, "dur": 33.157, + "args": { + "External id": 1422923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536226238.959, "dur": 29.483, + "args": { + "External id": 1422924,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536226290.194, "dur": 32.752, + "args": { + "External id": 1422925,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536226351.097, "dur": 22.435, + "args": { + "External id": 1422926,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536226388.724, "dur": 15.412, + "args": { + "External id": 1422927,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536226436.433, "dur": 51.033, + "args": { + "External id": 1422928,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536226492.807, "dur": 38.332, + "args": { + "External id": 1422929,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536226578.290, "dur": 304.780, + "args": { + "External id": 1422930,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536226683.491, "dur": 9.040, + "args": { + "External id": 1422931,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536226695.197, "dur": 3.156, + "args": { + "External id": 1422932,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536226699.946, "dur": 2.562, + "args": { + "External id": 1422933,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536226703.972, "dur": 4.642, + "args": { + "External id": 1422934,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536226766.285, "dur": 5.653, + "args": { + "External id": 1422935,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536226768.271, "dur": 3.500, + "args": { + "External id": 1422936,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536226773.805, "dur": 37.953, + "args": { + "External id": 1422937,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536226779.878, "dur": 2.105, + "args": { + "External id": 1422938,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536226813.478, "dur": 1.956, + "args": { + "External id": 1422939,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536226814.694, "dur": 0.660, + "args": { + "External id": 1422940,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536226816.345, "dur": 16.809, + "args": { + "External id": 1422941,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536226818.787, "dur": 0.616, + "args": { + "External id": 1422942,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536226923.550, "dur": 32.305, + "args": { + "External id": 1422943,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536226986.023, "dur": 19.437, + "args": { + "External id": 1422944,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536227015.500, "dur": 90.016, + "args": { + "External id": 1422945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536227119.516, "dur": 54.014, + "args": { + "External id": 1422946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536227187.708, "dur": 27.274, + "args": { + "External id": 1422947,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536227223.281, "dur": 37.703, + "args": { + "External id": 1422948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536227270.286, "dur": 33.740, + "args": { + "External id": 1422949,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536227312.229, "dur": 35.145, + "args": { + "External id": 1422950,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536227371.456, "dur": 30.557, + "args": { + "External id": 1422951,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536227438.194, "dur": 33.796, + "args": { + "External id": 1422952,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536227491.646, "dur": 22.138, + "args": { + "External id": 1422953,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536227532.373, "dur": 18.778, + "args": { + "External id": 1422954,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536227565.377, "dur": 19.675, + "args": { + "External id": 1422955,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227679.447, "dur": 18.512, + "args": { + "External id": 1422956,"Record function id": 0, "Ev Idx": 10859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227683.724, "dur": 13.159, + "args": { + "External id": 1422957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227688.962, "dur": 6.646, + "args": { + "External id": 1422958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227691.065, "dur": 4.404, + "args": { + "External id": 1422959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227702.735, "dur": 6.489, + "args": { + "External id": 1422960,"Record function id": 0, "Ev Idx": 10863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227704.286, "dur": 4.382, + "args": { + "External id": 1422961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227705.111, "dur": 2.784, + "args": { + "External id": 1422962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227706.067, "dur": 1.698, + "args": { + "External id": 1422963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227713.274, "dur": 5.301, + "args": { + "External id": 1422964,"Record function id": 0, "Ev Idx": 10867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227714.950, "dur": 3.111, + "args": { + "External id": 1422965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227715.572, "dur": 1.943, + "args": { + "External id": 1422966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227716.339, "dur": 1.073, + "args": { + "External id": 1422967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227722.319, "dur": 5.174, + "args": { + "External id": 1422968,"Record function id": 0, "Ev Idx": 10871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227723.816, "dur": 3.185, + "args": { + "External id": 1422969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227724.603, "dur": 1.929, + "args": { + "External id": 1422970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227725.323, "dur": 1.099, + "args": { + "External id": 1422971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227731.139, "dur": 7.717, + "args": { + "External id": 1422972,"Record function id": 0, "Ev Idx": 10875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227732.672, "dur": 5.662, + "args": { + "External id": 1422973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227733.437, "dur": 4.239, + "args": { + "External id": 1422974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227733.826, "dur": 3.771, + "args": { + "External id": 1422975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227746.464, "dur": 4.997, + "args": { + "External id": 1422976,"Record function id": 0, "Ev Idx": 10879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227747.766, "dur": 3.169, + "args": { + "External id": 1422977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227748.506, "dur": 1.795, + "args": { + "External id": 1422978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227748.988, "dur": 1.233, + "args": { + "External id": 1422979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227755.222, "dur": 4.821, + "args": { + "External id": 1422980,"Record function id": 0, "Ev Idx": 10883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227756.966, "dur": 2.572, + "args": { + "External id": 1422981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227757.639, "dur": 1.379, + "args": { + "External id": 1422982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227758.011, "dur": 0.886, + "args": { + "External id": 1422983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227763.854, "dur": 4.404, + "args": { + "External id": 1422984,"Record function id": 0, "Ev Idx": 10887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227765.281, "dur": 2.489, + "args": { + "External id": 1422985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227765.981, "dur": 1.317, + "args": { + "External id": 1422986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227766.301, "dur": 0.875, + "args": { + "External id": 1422987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227772.140, "dur": 4.644, + "args": { + "External id": 1422988,"Record function id": 0, "Ev Idx": 10891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536227773.786, "dur": 2.505, + "args": { + "External id": 1422989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227774.354, "dur": 1.457, + "args": { + "External id": 1422990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536227774.896, "dur": 0.788, + "args": { + "External id": 1422991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536227781.498, "dur": 68970.159, + "args": { + "External id": 1422992,"Record function id": 0, "Sequence number": 15109082, "Fwd thread id": 1, "Ev Idx": 10895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536227783.381, "dur": 68956.679, + "args": { + "External id": 1422993,"Sequence number": 15109082, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10896 + } + }, + { + "ph": "f", "id": 437, "pid": 2338710, "tid": 2379450, "ts": 6410536227783.381, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410536227820.856, "dur": 42.910, + "args": { + "External id": 1422994,"Record function id": 0, "Ev Idx": 10897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410536227872.332, "dur": 72.502, + "args": { + "External id": 1422995,"Record function id": 0, "Ev Idx": 10898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 2338710, "tid": 2379450, + "ts": 6410536227951.623, "dur": 68779.040, + "args": { + "External id": 1422996,"Record function id": 0, "Ev Idx": 10899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536228053.365, "dur": 49.523, + "args": { + "External id": 1422997,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536228118.978, "dur": 5.736, + "args": { + "External id": 1422998,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536228143.185, "dur": 67495.579, + "args": { + "External id": 1422999,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536228160.116, "dur": 67463.058, + "args": { + "External id": 1423000,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536228295.069, "dur": 24.006, + "args": { + "External id": 1423001,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536228345.576, "dur": 67220.473, + "args": { + "External id": 1423002,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536228349.013, "dur": 67215.675, + "args": { + "External id": 1423003,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536228354.599, "dur": 12.789, + "args": { + "External id": 1423004,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536228369.958, "dur": 67190.715, + "args": { + "External id": 1423005,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536295761.434, "dur": 14.552, + "args": { + "External id": 1423006,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536295765.442, "dur": 10.079, + "args": { + "External id": 1423007,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536295812.515, "dur": 446.210, + "args": { + "External id": 1423008,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536295846.102, "dur": 405.892, + "args": { + "External id": 1423009,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10912, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536295860.255, "dur": 385.076, + "args": { + "External id": 1423010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536296286.189, "dur": 2.854, + "args": { + "External id": 1423011,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10914, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296360.578, "dur": 9.267, + "args": { + "External id": 1423012,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296385.420, "dur": 58.935, + "args": { + "External id": 1423013,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296460.451, "dur": 2.872, + "args": { + "External id": 1423014,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296470.296, "dur": 17.164, + "args": { + "External id": 1423015,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296494.902, "dur": 1.032, + "args": { + "External id": 1423016,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296502.185, "dur": 12.123, + "args": { + "External id": 1423017,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296520.369, "dur": 0.873, + "args": { + "External id": 1423018,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296525.916, "dur": 14.300, + "args": { + "External id": 1423019,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296544.995, "dur": 0.989, + "args": { + "External id": 1423020,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296550.380, "dur": 12.397, + "args": { + "External id": 1423021,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296567.564, "dur": 1.483, + "args": { + "External id": 1423022,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296573.958, "dur": 13.812, + "args": { + "External id": 1423023,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296592.514, "dur": 1.031, + "args": { + "External id": 1423024,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296598.513, "dur": 12.113, + "args": { + "External id": 1423025,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296617.556, "dur": 1.107, + "args": { + "External id": 1423026,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296623.172, "dur": 13.100, + "args": { + "External id": 1423027,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536296640.760, "dur": 3.148, + "args": { + "External id": 1423028,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536296648.748, "dur": 12.492, + "args": { + "External id": 1423029,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536296774.003, "dur": 3388.442, + "args": { + "External id": 1423030,"Record function id": 0, "Ev Idx": 10933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410536296796.226, "dur": 1245.440, + "args": { + "External id": 1423031,"Record function id": 0, "Ev Idx": 10934 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410536296813.478, "dur": 443.448, + "args": { + "External id": 1423032,"Record function id": 0, "Ev Idx": 10935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296919.446, "dur": 4.450, + "args": { + "External id": 1423033,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296927.570, "dur": 0.994, + "args": { + "External id": 1423034,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296930.517, "dur": 0.845, + "args": { + "External id": 1423035,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296933.780, "dur": 0.974, + "args": { + "External id": 1423036,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296938.507, "dur": 1.010, + "args": { + "External id": 1423037,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296941.054, "dur": 1.180, + "args": { + "External id": 1423038,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296944.064, "dur": 1.126, + "args": { + "External id": 1423039,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296946.578, "dur": 4.398, + "args": { + "External id": 1423040,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296954.605, "dur": 1.039, + "args": { + "External id": 1423041,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536296957.566, "dur": 0.715, + "args": { + "External id": 1423042,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536296978.770, "dur": 234.585, + "args": { + "External id": 1423043,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536296998.038, "dur": 208.361, + "args": { + "External id": 1423044,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536297014.220, "dur": 17.297, + "args": { + "External id": 1423045,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536297035.997, "dur": 134.798, + "args": { + "External id": 1423046,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536297038.966, "dur": 131.261, + "args": { + "External id": 1423047,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297043.804, "dur": 6.234, + "args": { + "External id": 1423048,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536297052.384, "dur": 115.831, + "args": { + "External id": 1423049,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10952 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.3", "pid": 2338710, "tid": 2379450, + "ts": 6410536297360.354, "dur": 672.820, + "args": { + "External id": 1423050,"Record function id": 0, "Ev Idx": 10953 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410536297381.379, "dur": 637.752, + "args": { + "External id": 1423051,"Record function id": 0, "Ev Idx": 10954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536297475.465, "dur": 7.446, + "args": { + "External id": 1423052,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536297501.327, "dur": 33.175, + "args": { + "External id": 1423053,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297508.018, "dur": 1.966, + "args": { + "External id": 1423054,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297511.903, "dur": 1.088, + "args": { + "External id": 1423055,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297514.527, "dur": 2.929, + "args": { + "External id": 1423056,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297519.581, "dur": 0.404, + "args": { + "External id": 1423057,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297520.985, "dur": 0.619, + "args": { + "External id": 1423058,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297523.275, "dur": 0.450, + "args": { + "External id": 1423059,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297525.629, "dur": 0.477, + "args": { + "External id": 1423060,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297527.062, "dur": 0.464, + "args": { + "External id": 1423061,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297529.532, "dur": 0.446, + "args": { + "External id": 1423062,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536297548.042, "dur": 48.960, + "args": { + "External id": 1423063,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410536297634.032, "dur": 126.891, + "args": { + "External id": 1423064,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536297646.788, "dur": 4.367, + "args": { + "External id": 1423065,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410536297657.302, "dur": 14.375, + "args": { + "External id": 1423066,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410536297662.465, "dur": 8.753, + "args": { + "External id": 1423067,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297666.432, "dur": 3.251, + "args": { + "External id": 1423068,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536297679.336, "dur": 28.902, + "args": { + "External id": 1423069,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297681.568, "dur": 0.541, + "args": { + "External id": 1423070,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297683.347, "dur": 0.483, + "args": { + "External id": 1423071,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297685.604, "dur": 0.529, + "args": { + "External id": 1423072,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297687.898, "dur": 0.405, + "args": { + "External id": 1423073,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297689.303, "dur": 0.589, + "args": { + "External id": 1423074,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297691.906, "dur": 0.494, + "args": { + "External id": 1423075,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297697.718, "dur": 0.404, + "args": { + "External id": 1423076,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297699.794, "dur": 2.614, + "args": { + "External id": 1423077,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536297703.816, "dur": 0.507, + "args": { + "External id": 1423078,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536297719.990, "dur": 32.259, + "args": { + "External id": 1423079,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536297813.072, "dur": 131.192, + "args": { + "External id": 1423080,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536297841.877, "dur": 98.384, + "args": { + "External id": 1423081,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10984, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536297853.406, "dur": 81.913, + "args": { + "External id": 1423082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536297960.453, "dur": 2.251, + "args": { + "External id": 1423083,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 10986, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536298050.718, "dur": 2079.180, + "args": { + "External id": 1423084,"Sequence number": 15109081, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10987 + } + }, + { + "ph": "f", "id": 438, "pid": 2338710, "tid": 2379450, "ts": 6410536298050.718, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536298226.334, "dur": 126.545, + "args": { + "External id": 1423085,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536298403.881, "dur": 70.844, + "args": { + "External id": 1423086,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536298501.142, "dur": 64.903, + "args": { + "External id": 1423087,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536298580.406, "dur": 35.407, + "args": { + "External id": 1423088,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536298623.794, "dur": 36.770, + "args": { + "External id": 1423089,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536298668.140, "dur": 31.486, + "args": { + "External id": 1423090,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536298710.390, "dur": 33.012, + "args": { + "External id": 1423091,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536298776.039, "dur": 27.575, + "args": { + "External id": 1423092,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536298824.013, "dur": 33.474, + "args": { + "External id": 1423093,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536298884.534, "dur": 23.282, + "args": { + "External id": 1423094,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536298926.094, "dur": 16.430, + "args": { + "External id": 1423095,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536298954.601, "dur": 44.907, + "args": { + "External id": 1423096,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536299003.885, "dur": 37.850, + "args": { + "External id": 1423097,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536299115.919, "dur": 332.058, + "args": { + "External id": 1423098,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536299221.235, "dur": 10.635, + "args": { + "External id": 1423099,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536299234.375, "dur": 3.234, + "args": { + "External id": 1423100,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536299239.129, "dur": 2.786, + "args": { + "External id": 1423101,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536299243.028, "dur": 5.187, + "args": { + "External id": 1423102,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536299301.015, "dur": 5.584, + "args": { + "External id": 1423103,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536299303.144, "dur": 3.251, + "args": { + "External id": 1423104,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536299308.975, "dur": 37.222, + "args": { + "External id": 1423105,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536299315.452, "dur": 2.126, + "args": { + "External id": 1423106,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536299348.368, "dur": 1.922, + "args": { + "External id": 1423107,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536299349.533, "dur": 0.660, + "args": { + "External id": 1423108,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536299351.438, "dur": 16.789, + "args": { + "External id": 1423109,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536299353.989, "dur": 0.558, + "args": { + "External id": 1423110,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536299494.442, "dur": 34.233, + "args": { + "External id": 1423111,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536299547.796, "dur": 18.580, + "args": { + "External id": 1423112,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536299576.509, "dur": 60.208, + "args": { + "External id": 1423113,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536299645.279, "dur": 46.953, + "args": { + "External id": 1423114,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536299705.063, "dur": 26.553, + "args": { + "External id": 1423115,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536299739.066, "dur": 36.056, + "args": { + "External id": 1423116,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536299784.507, "dur": 31.450, + "args": { + "External id": 1423117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536299825.549, "dur": 33.915, + "args": { + "External id": 1423118,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536299879.640, "dur": 26.619, + "args": { + "External id": 1423119,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536299924.010, "dur": 28.464, + "args": { + "External id": 1423120,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536299967.450, "dur": 19.510, + "args": { + "External id": 1423121,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536300002.245, "dur": 17.048, + "args": { + "External id": 1423122,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536300033.862, "dur": 19.384, + "args": { + "External id": 1423123,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300189.580, "dur": 18.201, + "args": { + "External id": 1423124,"Record function id": 0, "Ev Idx": 11027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300193.884, "dur": 12.633, + "args": { + "External id": 1423125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300198.693, "dur": 6.713, + "args": { + "External id": 1423126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300200.850, "dur": 4.421, + "args": { + "External id": 1423127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300212.295, "dur": 9.487, + "args": { + "External id": 1423128,"Record function id": 0, "Ev Idx": 11031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300214.283, "dur": 6.967, + "args": { + "External id": 1423129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300215.157, "dur": 2.167, + "args": { + "External id": 1423130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300216.086, "dur": 1.139, + "args": { + "External id": 1423131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300225.692, "dur": 5.041, + "args": { + "External id": 1423132,"Record function id": 0, "Ev Idx": 11035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300226.988, "dur": 3.257, + "args": { + "External id": 1423133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300227.870, "dur": 1.854, + "args": { + "External id": 1423134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300228.518, "dur": 1.118, + "args": { + "External id": 1423135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300234.596, "dur": 5.400, + "args": { + "External id": 1423136,"Record function id": 0, "Ev Idx": 11039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300236.423, "dur": 3.070, + "args": { + "External id": 1423137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300237.029, "dur": 1.782, + "args": { + "External id": 1423138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300237.710, "dur": 1.020, + "args": { + "External id": 1423139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300243.768, "dur": 4.633, + "args": { + "External id": 1423140,"Record function id": 0, "Ev Idx": 11043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300245.279, "dur": 2.660, + "args": { + "External id": 1423141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300246.045, "dur": 1.367, + "args": { + "External id": 1423142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300246.503, "dur": 0.822, + "args": { + "External id": 1423143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300251.993, "dur": 7.367, + "args": { + "External id": 1423144,"Record function id": 0, "Ev Idx": 11047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300253.539, "dur": 5.350, + "args": { + "External id": 1423145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300254.301, "dur": 3.834, + "args": { + "External id": 1423146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300255.077, "dur": 2.970, + "args": { + "External id": 1423147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300263.143, "dur": 4.465, + "args": { + "External id": 1423148,"Record function id": 0, "Ev Idx": 11051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300264.619, "dur": 2.491, + "args": { + "External id": 1423149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300265.200, "dur": 1.402, + "args": { + "External id": 1423150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300265.563, "dur": 0.921, + "args": { + "External id": 1423151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300271.870, "dur": 4.736, + "args": { + "External id": 1423152,"Record function id": 0, "Ev Idx": 11055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300273.481, "dur": 2.642, + "args": { + "External id": 1423153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300274.008, "dur": 1.535, + "args": { + "External id": 1423154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300274.722, "dur": 0.655, + "args": { + "External id": 1423155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300280.764, "dur": 4.598, + "args": { + "External id": 1423156,"Record function id": 0, "Ev Idx": 11059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536300282.184, "dur": 2.706, + "args": { + "External id": 1423157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300282.911, "dur": 1.377, + "args": { + "External id": 1423158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536300283.367, "dur": 0.820, + "args": { + "External id": 1423159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536300290.114, "dur": 69821.715, + "args": { + "External id": 1423160,"Record function id": 0, "Sequence number": 15109080, "Fwd thread id": 1, "Ev Idx": 11063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536300291.930, "dur": 69808.353, + "args": { + "External id": 1423161,"Sequence number": 15109080, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11064 + } + }, + { + "ph": "f", "id": 439, "pid": 2338710, "tid": 2379450, "ts": 6410536300291.930, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410536300327.118, "dur": 46.190, + "args": { + "External id": 1423162,"Record function id": 0, "Ev Idx": 11065 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410536300382.895, "dur": 96.229, + "args": { + "External id": 1423163,"Record function id": 0, "Ev Idx": 11066 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 2338710, "tid": 2379450, + "ts": 6410536300488.363, "dur": 69600.287, + "args": { + "External id": 1423164,"Record function id": 0, "Ev Idx": 11067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536300600.489, "dur": 9.295, + "args": { + "External id": 1423165,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536300625.160, "dur": 5.606, + "args": { + "External id": 1423166,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536300647.058, "dur": 68226.864, + "args": { + "External id": 1423167,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536300663.349, "dur": 68194.336, + "args": { + "External id": 1423168,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536300785.742, "dur": 21.086, + "args": { + "External id": 1423169,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536300829.730, "dur": 67967.951, + "args": { + "External id": 1423170,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536300832.759, "dur": 67963.485, + "args": { + "External id": 1423171,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536300838.054, "dur": 10.866, + "args": { + "External id": 1423172,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536300851.372, "dur": 67937.916, + "args": { + "External id": 1423173,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536369008.919, "dur": 16.047, + "args": { + "External id": 1423174,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536369013.298, "dur": 11.130, + "args": { + "External id": 1423175,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369096.745, "dur": 496.816, + "args": { + "External id": 1423176,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536369133.157, "dur": 454.065, + "args": { + "External id": 1423177,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11080, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536369148.037, "dur": 430.235, + "args": { + "External id": 1423178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536369620.412, "dur": 2.643, + "args": { + "External id": 1423179,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11082, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369702.559, "dur": 8.110, + "args": { + "External id": 1423180,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369731.480, "dur": 43.628, + "args": { + "External id": 1423181,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369787.573, "dur": 4.105, + "args": { + "External id": 1423182,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369798.100, "dur": 15.433, + "args": { + "External id": 1423183,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369820.077, "dur": 0.878, + "args": { + "External id": 1423184,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369826.580, "dur": 12.717, + "args": { + "External id": 1423185,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369845.072, "dur": 1.118, + "args": { + "External id": 1423186,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369851.392, "dur": 11.661, + "args": { + "External id": 1423187,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369868.178, "dur": 0.953, + "args": { + "External id": 1423188,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369873.989, "dur": 11.829, + "args": { + "External id": 1423189,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369890.654, "dur": 1.114, + "args": { + "External id": 1423190,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369896.447, "dur": 12.142, + "args": { + "External id": 1423191,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369914.376, "dur": 0.825, + "args": { + "External id": 1423192,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369920.245, "dur": 11.312, + "args": { + "External id": 1423193,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369939.078, "dur": 0.949, + "args": { + "External id": 1423194,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369944.751, "dur": 14.399, + "args": { + "External id": 1423195,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536369964.086, "dur": 0.865, + "args": { + "External id": 1423196,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536369969.807, "dur": 12.633, + "args": { + "External id": 1423197,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536370133.291, "dur": 3442.803, + "args": { + "External id": 1423198,"Record function id": 0, "Ev Idx": 11101 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410536370159.761, "dur": 1242.360, + "args": { + "External id": 1423199,"Record function id": 0, "Ev Idx": 11102 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410536370178.573, "dur": 402.067, + "args": { + "External id": 1423200,"Record function id": 0, "Ev Idx": 11103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370281.592, "dur": 7.907, + "args": { + "External id": 1423201,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370293.880, "dur": 0.902, + "args": { + "External id": 1423202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370297.514, "dur": 1.046, + "args": { + "External id": 1423203,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370300.834, "dur": 0.980, + "args": { + "External id": 1423204,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370305.739, "dur": 0.807, + "args": { + "External id": 1423205,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370308.684, "dur": 1.334, + "args": { + "External id": 1423206,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370311.959, "dur": 1.151, + "args": { + "External id": 1423207,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370314.861, "dur": 2.144, + "args": { + "External id": 1423208,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370320.477, "dur": 3.016, + "args": { + "External id": 1423209,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536370325.046, "dur": 0.829, + "args": { + "External id": 1423210,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536370347.408, "dur": 190.858, + "args": { + "External id": 1423211,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536370368.158, "dur": 163.849, + "args": { + "External id": 1423212,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536370385.225, "dur": 15.587, + "args": { + "External id": 1423213,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536370405.374, "dur": 93.906, + "args": { + "External id": 1423214,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 11117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536370408.321, "dur": 90.453, + "args": { + "External id": 1423215,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 11118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370413.202, "dur": 22.384, + "args": { + "External id": 1423216,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536370438.599, "dur": 59.314, + "args": { + "External id": 1423217,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 11120 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.2", "pid": 2338710, "tid": 2379450, + "ts": 6410536370683.270, "dur": 709.990, + "args": { + "External id": 1423218,"Record function id": 0, "Ev Idx": 11121 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410536370703.820, "dur": 674.638, + "args": { + "External id": 1423219,"Record function id": 0, "Ev Idx": 11122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536370779.614, "dur": 6.000, + "args": { + "External id": 1423220,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536370803.012, "dur": 33.676, + "args": { + "External id": 1423221,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370809.054, "dur": 1.888, + "args": { + "External id": 1423222,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370813.848, "dur": 0.676, + "args": { + "External id": 1423223,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370816.584, "dur": 0.446, + "args": { + "External id": 1423224,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370818.820, "dur": 3.261, + "args": { + "External id": 1423225,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370823.362, "dur": 0.625, + "args": { + "External id": 1423226,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370826.134, "dur": 0.427, + "args": { + "External id": 1423227,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370828.511, "dur": 0.366, + "args": { + "External id": 1423228,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370830.016, "dur": 0.442, + "args": { + "External id": 1423229,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370832.297, "dur": 0.399, + "args": { + "External id": 1423230,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536370849.677, "dur": 46.860, + "args": { + "External id": 1423231,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410536370933.002, "dur": 172.480, + "args": { + "External id": 1423232,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 11135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536370945.788, "dur": 3.938, + "args": { + "External id": 1423233,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410536370956.352, "dur": 11.832, + "args": { + "External id": 1423234,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410536370961.503, "dur": 6.204, + "args": { + "External id": 1423235,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 11138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370965.655, "dur": 0.638, + "args": { + "External id": 1423236,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536370975.771, "dur": 29.174, + "args": { + "External id": 1423237,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370978.120, "dur": 2.854, + "args": { + "External id": 1423238,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370982.864, "dur": 0.480, + "args": { + "External id": 1423239,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370985.256, "dur": 0.609, + "args": { + "External id": 1423240,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370987.355, "dur": 0.400, + "args": { + "External id": 1423241,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370988.910, "dur": 0.687, + "args": { + "External id": 1423242,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370991.129, "dur": 0.655, + "args": { + "External id": 1423243,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370993.328, "dur": 0.457, + "args": { + "External id": 1423244,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370994.837, "dur": 0.516, + "args": { + "External id": 1423245,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536370997.293, "dur": 2.564, + "args": { + "External id": 1423246,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536371017.894, "dur": 74.812, + "args": { + "External id": 1423247,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536371164.180, "dur": 132.089, + "args": { + "External id": 1423248,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 11151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536371192.019, "dur": 100.297, + "args": { + "External id": 1423249,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11152, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536371202.889, "dur": 84.739, + "args": { + "External id": 1423250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 11153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536371314.732, "dur": 2.098, + "args": { + "External id": 1423251,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11154, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536371410.816, "dur": 2141.589, + "args": { + "External id": 1423252,"Sequence number": 15109079, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11155 + } + }, + { + "ph": "f", "id": 440, "pid": 2338710, "tid": 2379450, "ts": 6410536371410.816, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536371563.044, "dur": 123.872, + "args": { + "External id": 1423253,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 11156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536371738.629, "dur": 46.774, + "args": { + "External id": 1423254,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 11157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536371807.778, "dur": 57.296, + "args": { + "External id": 1423255,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 11158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536371875.973, "dur": 36.655, + "args": { + "External id": 1423256,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536371919.462, "dur": 49.544, + "args": { + "External id": 1423257,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536371981.193, "dur": 48.281, + "args": { + "External id": 1423258,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536372046.368, "dur": 82.964, + "args": { + "External id": 1423259,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536372174.864, "dur": 31.689, + "args": { + "External id": 1423260,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 11163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536372229.754, "dur": 32.642, + "args": { + "External id": 1423261,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536372289.354, "dur": 22.241, + "args": { + "External id": 1423262,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536372326.044, "dur": 16.434, + "args": { + "External id": 1423263,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536372356.543, "dur": 48.586, + "args": { + "External id": 1423264,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536372410.181, "dur": 57.282, + "args": { + "External id": 1423265,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536372516.805, "dur": 313.873, + "args": { + "External id": 1423266,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536372624.370, "dur": 8.780, + "args": { + "External id": 1423267,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536372640.477, "dur": 3.680, + "args": { + "External id": 1423268,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536372645.579, "dur": 2.764, + "args": { + "External id": 1423269,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536372649.535, "dur": 4.278, + "args": { + "External id": 1423270,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536372711.400, "dur": 5.506, + "args": { + "External id": 1423271,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536372713.468, "dur": 3.264, + "args": { + "External id": 1423272,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536372718.852, "dur": 37.825, + "args": { + "External id": 1423273,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536372725.223, "dur": 2.218, + "args": { + "External id": 1423274,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536372758.795, "dur": 1.780, + "args": { + "External id": 1423275,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536372759.671, "dur": 0.799, + "args": { + "External id": 1423276,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536372761.981, "dur": 18.836, + "args": { + "External id": 1423277,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536372764.589, "dur": 0.812, + "args": { + "External id": 1423278,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536372872.439, "dur": 32.151, + "args": { + "External id": 1423279,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536372926.593, "dur": 18.702, + "args": { + "External id": 1423280,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536372955.172, "dur": 51.873, + "args": { + "External id": 1423281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536373016.640, "dur": 86.138, + "args": { + "External id": 1423282,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536373121.686, "dur": 32.334, + "args": { + "External id": 1423283,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536373161.900, "dur": 37.450, + "args": { + "External id": 1423284,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536373208.141, "dur": 31.767, + "args": { + "External id": 1423285,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536373249.203, "dur": 35.203, + "args": { + "External id": 1423286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536373307.103, "dur": 27.669, + "args": { + "External id": 1423287,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536373352.560, "dur": 29.806, + "args": { + "External id": 1423288,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536373398.889, "dur": 37.108, + "args": { + "External id": 1423289,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536373458.586, "dur": 21.461, + "args": { + "External id": 1423290,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536373495.497, "dur": 19.356, + "args": { + "External id": 1423291,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373606.934, "dur": 18.073, + "args": { + "External id": 1423292,"Record function id": 0, "Ev Idx": 11195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373611.225, "dur": 12.589, + "args": { + "External id": 1423293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373616.153, "dur": 6.490, + "args": { + "External id": 1423294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373618.009, "dur": 4.496, + "args": { + "External id": 1423295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373629.813, "dur": 6.559, + "args": { + "External id": 1423296,"Record function id": 0, "Ev Idx": 11199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373631.798, "dur": 3.980, + "args": { + "External id": 1423297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373632.807, "dur": 2.415, + "args": { + "External id": 1423298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373633.875, "dur": 1.212, + "args": { + "External id": 1423299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373640.339, "dur": 5.004, + "args": { + "External id": 1423300,"Record function id": 0, "Ev Idx": 11203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373641.861, "dur": 3.001, + "args": { + "External id": 1423301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373642.631, "dur": 1.672, + "args": { + "External id": 1423302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373643.172, "dur": 1.055, + "args": { + "External id": 1423303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373649.274, "dur": 8.709, + "args": { + "External id": 1423304,"Record function id": 0, "Ev Idx": 11207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373651.160, "dur": 6.317, + "args": { + "External id": 1423305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373651.794, "dur": 5.080, + "args": { + "External id": 1423306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373652.681, "dur": 4.107, + "args": { + "External id": 1423307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373661.845, "dur": 7.200, + "args": { + "External id": 1423308,"Record function id": 0, "Ev Idx": 11211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373663.249, "dur": 5.299, + "args": { + "External id": 1423309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373663.823, "dur": 4.055, + "args": { + "External id": 1423310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373664.580, "dur": 3.219, + "args": { + "External id": 1423311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373672.693, "dur": 4.534, + "args": { + "External id": 1423312,"Record function id": 0, "Ev Idx": 11215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373674.251, "dur": 2.488, + "args": { + "External id": 1423313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373674.867, "dur": 1.174, + "args": { + "External id": 1423314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373675.194, "dur": 0.765, + "args": { + "External id": 1423315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373681.191, "dur": 4.669, + "args": { + "External id": 1423316,"Record function id": 0, "Ev Idx": 11219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373682.854, "dur": 2.509, + "args": { + "External id": 1423317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373683.454, "dur": 1.433, + "args": { + "External id": 1423318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373683.980, "dur": 0.782, + "args": { + "External id": 1423319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373689.598, "dur": 5.484, + "args": { + "External id": 1423320,"Record function id": 0, "Ev Idx": 11223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373691.501, "dur": 3.099, + "args": { + "External id": 1423321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373692.109, "dur": 1.999, + "args": { + "External id": 1423322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373693.054, "dur": 0.930, + "args": { + "External id": 1423323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373698.854, "dur": 5.013, + "args": { + "External id": 1423324,"Record function id": 0, "Ev Idx": 11227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536373700.267, "dur": 3.078, + "args": { + "External id": 1423325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373701.056, "dur": 1.773, + "args": { + "External id": 1423326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536373701.780, "dur": 0.954, + "args": { + "External id": 1423327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536373708.459, "dur": 64025.579, + "args": { + "External id": 1423328,"Record function id": 0, "Sequence number": 15109078, "Fwd thread id": 1, "Ev Idx": 11231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536373710.436, "dur": 64013.631, + "args": { + "External id": 1423329,"Sequence number": 15109078, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11232 + } + }, + { + "ph": "f", "id": 441, "pid": 2338710, "tid": 2379450, "ts": 6410536373710.436, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410536373745.104, "dur": 46.728, + "args": { + "External id": 1423330,"Record function id": 0, "Ev Idx": 11233 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410536373801.314, "dur": 72.710, + "args": { + "External id": 1423331,"Record function id": 0, "Ev Idx": 11234 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 2338710, "tid": 2379450, + "ts": 6410536373880.929, "dur": 63833.875, + "args": { + "External id": 1423332,"Record function id": 0, "Ev Idx": 11235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536373985.503, "dur": 7.979, + "args": { + "External id": 1423333,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536374004.697, "dur": 5.358, + "args": { + "External id": 1423334,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536374026.436, "dur": 62532.145, + "args": { + "External id": 1423335,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536374042.683, "dur": 62500.996, + "args": { + "External id": 1423336,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536374199.121, "dur": 23.744, + "args": { + "External id": 1423337,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536374257.872, "dur": 62235.358, + "args": { + "External id": 1423338,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536374261.267, "dur": 62230.787, + "args": { + "External id": 1423339,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536374267.528, "dur": 16.918, + "args": { + "External id": 1423340,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536374290.508, "dur": 62197.623, + "args": { + "External id": 1423341,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536436684.237, "dur": 14.074, + "args": { + "External id": 1423342,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536436688.185, "dur": 9.680, + "args": { + "External id": 1423343,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536436737.414, "dur": 461.174, + "args": { + "External id": 1423344,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536436773.234, "dur": 418.776, + "args": { + "External id": 1423345,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11248, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536436790.050, "dur": 395.306, + "args": { + "External id": 1423346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536437225.823, "dur": 2.586, + "args": { + "External id": 1423347,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11250, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437302.498, "dur": 7.799, + "args": { + "External id": 1423348,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437327.154, "dur": 41.761, + "args": { + "External id": 1423349,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437381.161, "dur": 4.054, + "args": { + "External id": 1423350,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437391.732, "dur": 15.951, + "args": { + "External id": 1423351,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437432.593, "dur": 2.261, + "args": { + "External id": 1423352,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437442.205, "dur": 17.460, + "args": { + "External id": 1423353,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437475.265, "dur": 0.942, + "args": { + "External id": 1423354,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437481.260, "dur": 14.507, + "args": { + "External id": 1423355,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437501.147, "dur": 1.239, + "args": { + "External id": 1423356,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437507.254, "dur": 12.591, + "args": { + "External id": 1423357,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437524.284, "dur": 1.270, + "args": { + "External id": 1423358,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437530.200, "dur": 14.621, + "args": { + "External id": 1423359,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437552.126, "dur": 0.818, + "args": { + "External id": 1423360,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437576.191, "dur": 12.323, + "args": { + "External id": 1423361,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437600.282, "dur": 0.914, + "args": { + "External id": 1423362,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437606.276, "dur": 13.549, + "args": { + "External id": 1423363,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536437624.665, "dur": 0.918, + "args": { + "External id": 1423364,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536437630.192, "dur": 12.013, + "args": { + "External id": 1423365,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536437753.481, "dur": 3386.369, + "args": { + "External id": 1423366,"Record function id": 0, "Ev Idx": 11269 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410536437776.851, "dur": 1253.959, + "args": { + "External id": 1423367,"Record function id": 0, "Ev Idx": 11270 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410536437794.550, "dur": 425.923, + "args": { + "External id": 1423368,"Record function id": 0, "Ev Idx": 11271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437898.654, "dur": 7.602, + "args": { + "External id": 1423369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437910.165, "dur": 1.089, + "args": { + "External id": 1423370,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437913.767, "dur": 0.901, + "args": { + "External id": 1423371,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437916.705, "dur": 0.969, + "args": { + "External id": 1423372,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437921.083, "dur": 0.952, + "args": { + "External id": 1423373,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437923.802, "dur": 0.897, + "args": { + "External id": 1423374,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437926.597, "dur": 1.059, + "args": { + "External id": 1423375,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437929.474, "dur": 1.771, + "args": { + "External id": 1423376,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437935.311, "dur": 3.079, + "args": { + "External id": 1423377,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536437940.107, "dur": 0.896, + "args": { + "External id": 1423378,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536437962.736, "dur": 215.992, + "args": { + "External id": 1423379,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536437982.657, "dur": 190.089, + "args": { + "External id": 1423380,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536437998.968, "dur": 17.887, + "args": { + "External id": 1423381,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536438021.150, "dur": 119.704, + "args": { + "External id": 1423382,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 11285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536438024.114, "dur": 116.162, + "args": { + "External id": 1423383,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 11286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438029.029, "dur": 7.025, + "args": { + "External id": 1423384,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536438040.215, "dur": 98.825, + "args": { + "External id": 1423385,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 11288 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.1", "pid": 2338710, "tid": 2379450, + "ts": 6410536438325.106, "dur": 697.242, + "args": { + "External id": 1423386,"Record function id": 0, "Ev Idx": 11289 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410536438348.766, "dur": 658.509, + "args": { + "External id": 1423387,"Record function id": 0, "Ev Idx": 11290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536438446.447, "dur": 8.315, + "args": { + "External id": 1423388,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536438472.547, "dur": 32.119, + "args": { + "External id": 1423389,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438478.618, "dur": 2.203, + "args": { + "External id": 1423390,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438483.092, "dur": 0.801, + "args": { + "External id": 1423391,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438485.846, "dur": 0.527, + "args": { + "External id": 1423392,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438487.594, "dur": 2.820, + "args": { + "External id": 1423393,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438491.707, "dur": 0.623, + "args": { + "External id": 1423394,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438494.080, "dur": 0.307, + "args": { + "External id": 1423395,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438495.559, "dur": 0.435, + "args": { + "External id": 1423396,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438497.746, "dur": 0.341, + "args": { + "External id": 1423397,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438499.854, "dur": 0.451, + "args": { + "External id": 1423398,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536438518.565, "dur": 49.709, + "args": { + "External id": 1423399,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410536438605.353, "dur": 125.172, + "args": { + "External id": 1423400,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 11303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536438617.267, "dur": 3.943, + "args": { + "External id": 1423401,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410536438626.911, "dur": 11.410, + "args": { + "External id": 1423402,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410536438631.858, "dur": 5.987, + "args": { + "External id": 1423403,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 11306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438635.553, "dur": 0.731, + "args": { + "External id": 1423404,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536438645.793, "dur": 29.241, + "args": { + "External id": 1423405,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438647.898, "dur": 2.715, + "args": { + "External id": 1423406,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438652.223, "dur": 0.604, + "args": { + "External id": 1423407,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438654.453, "dur": 0.466, + "args": { + "External id": 1423408,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438656.698, "dur": 0.451, + "args": { + "External id": 1423409,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438658.101, "dur": 0.620, + "args": { + "External id": 1423410,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438660.133, "dur": 0.427, + "args": { + "External id": 1423411,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438662.356, "dur": 0.663, + "args": { + "External id": 1423412,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438664.042, "dur": 0.434, + "args": { + "External id": 1423413,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536438666.067, "dur": 2.754, + "args": { + "External id": 1423414,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536438686.766, "dur": 35.241, + "args": { + "External id": 1423415,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536438788.441, "dur": 139.324, + "args": { + "External id": 1423416,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 11319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536438821.533, "dur": 102.325, + "args": { + "External id": 1423417,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11320, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536438832.748, "dur": 86.296, + "args": { + "External id": 1423418,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 11321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536438945.080, "dur": 2.634, + "args": { + "External id": 1423419,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11322, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536439039.533, "dur": 2074.226, + "args": { + "External id": 1423420,"Sequence number": 15109077, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11323 + } + }, + { + "ph": "f", "id": 442, "pid": 2338710, "tid": 2379450, "ts": 6410536439039.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536439216.835, "dur": 123.355, + "args": { + "External id": 1423421,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 11324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536439390.778, "dur": 65.595, + "args": { + "External id": 1423422,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 11325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536439483.508, "dur": 62.091, + "args": { + "External id": 1423423,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 11326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536439556.547, "dur": 36.248, + "args": { + "External id": 1423424,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536439600.750, "dur": 36.419, + "args": { + "External id": 1423425,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536439645.801, "dur": 31.662, + "args": { + "External id": 1423426,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536439687.925, "dur": 32.912, + "args": { + "External id": 1423427,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536439751.266, "dur": 27.920, + "args": { + "External id": 1423428,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 11331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536439800.363, "dur": 31.635, + "args": { + "External id": 1423429,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536439857.396, "dur": 21.106, + "args": { + "External id": 1423430,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536439892.358, "dur": 16.717, + "args": { + "External id": 1423431,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536439921.403, "dur": 44.410, + "args": { + "External id": 1423432,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536439970.174, "dur": 38.214, + "args": { + "External id": 1423433,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536440042.186, "dur": 366.779, + "args": { + "External id": 1423434,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536440191.276, "dur": 10.668, + "args": { + "External id": 1423435,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536440204.984, "dur": 4.245, + "args": { + "External id": 1423436,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536440210.605, "dur": 2.205, + "args": { + "External id": 1423437,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536440213.739, "dur": 4.374, + "args": { + "External id": 1423438,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536440286.002, "dur": 5.959, + "args": { + "External id": 1423439,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536440288.376, "dur": 3.412, + "args": { + "External id": 1423440,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536440294.508, "dur": 38.900, + "args": { + "External id": 1423441,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536440301.014, "dur": 1.914, + "args": { + "External id": 1423442,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536440335.202, "dur": 2.114, + "args": { + "External id": 1423443,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536440336.517, "dur": 0.674, + "args": { + "External id": 1423444,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536440338.531, "dur": 16.978, + "args": { + "External id": 1423445,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536440340.707, "dur": 0.517, + "args": { + "External id": 1423446,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536440477.440, "dur": 37.324, + "args": { + "External id": 1423447,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536440533.495, "dur": 19.338, + "args": { + "External id": 1423448,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536440562.860, "dur": 59.786, + "args": { + "External id": 1423449,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536440631.715, "dur": 45.930, + "args": { + "External id": 1423450,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536440689.646, "dur": 25.032, + "args": { + "External id": 1423451,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536440721.369, "dur": 36.287, + "args": { + "External id": 1423452,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536440765.811, "dur": 34.037, + "args": { + "External id": 1423453,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536440808.070, "dur": 38.950, + "args": { + "External id": 1423454,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536440867.506, "dur": 29.849, + "args": { + "External id": 1423455,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536440914.555, "dur": 26.793, + "args": { + "External id": 1423456,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536440957.278, "dur": 19.123, + "args": { + "External id": 1423457,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536440993.195, "dur": 16.334, + "args": { + "External id": 1423458,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536441022.279, "dur": 16.756, + "args": { + "External id": 1423459,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441166.314, "dur": 18.375, + "args": { + "External id": 1423460,"Record function id": 0, "Ev Idx": 11363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441170.813, "dur": 12.746, + "args": { + "External id": 1423461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441175.773, "dur": 6.554, + "args": { + "External id": 1423462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441177.510, "dur": 4.616, + "args": { + "External id": 1423463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441189.214, "dur": 6.921, + "args": { + "External id": 1423464,"Record function id": 0, "Ev Idx": 11367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441191.099, "dur": 4.475, + "args": { + "External id": 1423465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441191.986, "dur": 2.689, + "args": { + "External id": 1423466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441192.926, "dur": 1.606, + "args": { + "External id": 1423467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441200.078, "dur": 5.674, + "args": { + "External id": 1423468,"Record function id": 0, "Ev Idx": 11371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441201.972, "dur": 3.323, + "args": { + "External id": 1423469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441202.664, "dur": 2.094, + "args": { + "External id": 1423470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441203.762, "dur": 0.917, + "args": { + "External id": 1423471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441209.534, "dur": 5.658, + "args": { + "External id": 1423472,"Record function id": 0, "Ev Idx": 11375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441211.175, "dur": 3.531, + "args": { + "External id": 1423473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441212.030, "dur": 2.102, + "args": { + "External id": 1423474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441212.837, "dur": 1.222, + "args": { + "External id": 1423475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441229.474, "dur": 7.034, + "args": { + "External id": 1423476,"Record function id": 0, "Ev Idx": 11379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441230.846, "dur": 5.126, + "args": { + "External id": 1423477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441231.474, "dur": 3.977, + "args": { + "External id": 1423478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441232.075, "dur": 3.253, + "args": { + "External id": 1423479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441240.311, "dur": 5.035, + "args": { + "External id": 1423480,"Record function id": 0, "Ev Idx": 11383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441241.957, "dur": 2.932, + "args": { + "External id": 1423481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441242.701, "dur": 1.663, + "args": { + "External id": 1423482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441243.090, "dur": 1.189, + "args": { + "External id": 1423483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441249.036, "dur": 4.496, + "args": { + "External id": 1423484,"Record function id": 0, "Ev Idx": 11387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441250.567, "dur": 2.493, + "args": { + "External id": 1423485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441251.231, "dur": 1.281, + "args": { + "External id": 1423486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441251.565, "dur": 0.829, + "args": { + "External id": 1423487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441257.642, "dur": 5.805, + "args": { + "External id": 1423488,"Record function id": 0, "Ev Idx": 11391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441258.889, "dur": 4.040, + "args": { + "External id": 1423489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441259.486, "dur": 2.948, + "args": { + "External id": 1423490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441261.626, "dur": 0.672, + "args": { + "External id": 1423491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441267.637, "dur": 4.195, + "args": { + "External id": 1423492,"Record function id": 0, "Ev Idx": 11395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536441268.880, "dur": 2.485, + "args": { + "External id": 1423493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441269.543, "dur": 1.282, + "args": { + "External id": 1423494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536441269.902, "dur": 0.797, + "args": { + "External id": 1423495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536441276.339, "dur": 62218.700, + "args": { + "External id": 1423496,"Record function id": 0, "Sequence number": 15109076, "Fwd thread id": 1, "Ev Idx": 11399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536441278.027, "dur": 62204.913, + "args": { + "External id": 1423497,"Sequence number": 15109076, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11400 + } + }, + { + "ph": "f", "id": 443, "pid": 2338710, "tid": 2379450, "ts": 6410536441278.027, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410536441314.091, "dur": 46.158, + "args": { + "External id": 1423498,"Record function id": 0, "Ev Idx": 11401 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410536441369.725, "dur": 98.401, + "args": { + "External id": 1423499,"Record function id": 0, "Ev Idx": 11402 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 2338710, "tid": 2379450, + "ts": 6410536441477.159, "dur": 61995.582, + "args": { + "External id": 1423500,"Record function id": 0, "Ev Idx": 11403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536441586.250, "dur": 8.611, + "args": { + "External id": 1423501,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536441606.560, "dur": 5.853, + "args": { + "External id": 1423502,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536441628.484, "dur": 60668.775, + "args": { + "External id": 1423503,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536441644.360, "dur": 60637.656, + "args": { + "External id": 1423504,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536441783.942, "dur": 20.826, + "args": { + "External id": 1423505,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536441828.093, "dur": 60395.475, + "args": { + "External id": 1423506,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536441831.307, "dur": 60391.024, + "args": { + "External id": 1423507,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536441849.931, "dur": 13.353, + "args": { + "External id": 1423508,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536441865.987, "dur": 60350.677, + "args": { + "External id": 1423509,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536502436.652, "dur": 16.026, + "args": { + "External id": 1423510,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536502440.949, "dur": 11.133, + "args": { + "External id": 1423511,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536502491.002, "dur": 468.061, + "args": { + "External id": 1423512,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536502525.502, "dur": 427.578, + "args": { + "External id": 1423513,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11416, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536502540.092, "dur": 407.025, + "args": { + "External id": 1423514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536502980.418, "dur": 2.786, + "args": { + "External id": 1423515,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11418, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503096.806, "dur": 11.009, + "args": { + "External id": 1423516,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503125.183, "dur": 45.558, + "args": { + "External id": 1423517,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503184.448, "dur": 2.133, + "args": { + "External id": 1423518,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503192.758, "dur": 16.799, + "args": { + "External id": 1423519,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503216.713, "dur": 1.126, + "args": { + "External id": 1423520,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503223.126, "dur": 12.576, + "args": { + "External id": 1423521,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503241.761, "dur": 1.060, + "args": { + "External id": 1423522,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503247.753, "dur": 13.576, + "args": { + "External id": 1423523,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503266.654, "dur": 1.074, + "args": { + "External id": 1423524,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503272.661, "dur": 12.814, + "args": { + "External id": 1423525,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503290.522, "dur": 1.327, + "args": { + "External id": 1423526,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503296.340, "dur": 13.022, + "args": { + "External id": 1423527,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503315.961, "dur": 1.152, + "args": { + "External id": 1423528,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503321.532, "dur": 12.147, + "args": { + "External id": 1423529,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503338.177, "dur": 1.086, + "args": { + "External id": 1423530,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503343.507, "dur": 11.781, + "args": { + "External id": 1423531,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503359.877, "dur": 3.871, + "args": { + "External id": 1423532,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503367.963, "dur": 11.738, + "args": { + "External id": 1423533,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536503518.116, "dur": 3404.311, + "args": { + "External id": 1423534,"Record function id": 0, "Ev Idx": 11437 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410536503542.831, "dur": 1257.289, + "args": { + "External id": 1423535,"Record function id": 0, "Ev Idx": 11438 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410536503562.058, "dur": 378.735, + "args": { + "External id": 1423536,"Record function id": 0, "Ev Idx": 11439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503664.122, "dur": 5.386, + "args": { + "External id": 1423537,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503673.436, "dur": 1.197, + "args": { + "External id": 1423538,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503678.668, "dur": 1.055, + "args": { + "External id": 1423539,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503681.562, "dur": 0.857, + "args": { + "External id": 1423540,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503684.026, "dur": 1.063, + "args": { + "External id": 1423541,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503687.338, "dur": 1.136, + "args": { + "External id": 1423542,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503692.155, "dur": 1.079, + "args": { + "External id": 1423543,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503694.871, "dur": 4.768, + "args": { + "External id": 1423544,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503701.610, "dur": 1.193, + "args": { + "External id": 1423545,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536503704.386, "dur": 0.978, + "args": { + "External id": 1423546,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536503735.281, "dur": 168.602, + "args": { + "External id": 1423547,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536503754.394, "dur": 144.254, + "args": { + "External id": 1423548,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536503770.142, "dur": 16.319, + "args": { + "External id": 1423549,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536503790.651, "dur": 74.170, + "args": { + "External id": 1423550,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 11453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536503793.629, "dur": 70.718, + "args": { + "External id": 1423551,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 11454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536503797.985, "dur": 6.168, + "args": { + "External id": 1423552,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536503805.882, "dur": 57.511, + "args": { + "External id": 1423553,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 11456 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.0", "pid": 2338710, "tid": 2379450, + "ts": 6410536504047.070, "dur": 743.788, + "args": { + "External id": 1423554,"Record function id": 0, "Ev Idx": 11457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410536504110.642, "dur": 665.109, + "args": { + "External id": 1423555,"Record function id": 0, "Ev Idx": 11458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536504191.930, "dur": 9.027, + "args": { + "External id": 1423556,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536504218.794, "dur": 31.167, + "args": { + "External id": 1423557,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504224.941, "dur": 2.165, + "args": { + "External id": 1423558,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504229.231, "dur": 0.562, + "args": { + "External id": 1423559,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504231.442, "dur": 2.279, + "args": { + "External id": 1423560,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504235.443, "dur": 0.338, + "args": { + "External id": 1423561,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504236.797, "dur": 0.627, + "args": { + "External id": 1423562,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504239.226, "dur": 0.441, + "args": { + "External id": 1423563,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504241.462, "dur": 0.380, + "args": { + "External id": 1423564,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504243.272, "dur": 0.586, + "args": { + "External id": 1423565,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504245.092, "dur": 0.390, + "args": { + "External id": 1423566,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536504262.459, "dur": 54.120, + "args": { + "External id": 1423567,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2379450, + "ts": 6410536504353.550, "dur": 154.057, + "args": { + "External id": 1423568,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 11471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536504366.242, "dur": 4.407, + "args": { + "External id": 1423569,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2379450, + "ts": 6410536504376.693, "dur": 14.575, + "args": { + "External id": 1423570,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2379450, + "ts": 6410536504381.897, "dur": 8.899, + "args": { + "External id": 1423571,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 11474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504386.089, "dur": 3.185, + "args": { + "External id": 1423572,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2379450, + "ts": 6410536504399.037, "dur": 43.010, + "args": { + "External id": 1423573,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504401.622, "dur": 0.473, + "args": { + "External id": 1423574,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504403.552, "dur": 0.421, + "args": { + "External id": 1423575,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504405.362, "dur": 0.612, + "args": { + "External id": 1423576,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504407.602, "dur": 0.835, + "args": { + "External id": 1423577,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504409.333, "dur": 0.385, + "args": { + "External id": 1423578,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504411.105, "dur": 0.636, + "args": { + "External id": 1423579,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504413.264, "dur": 16.347, + "args": { + "External id": 1423580,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504432.456, "dur": 2.630, + "args": { + "External id": 1423581,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536504436.554, "dur": 0.381, + "args": { + "External id": 1423582,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536504459.824, "dur": 38.418, + "args": { + "External id": 1423583,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536504562.976, "dur": 132.940, + "args": { + "External id": 1423584,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 11487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536504594.554, "dur": 97.357, + "args": { + "External id": 1423585,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11488, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536504605.976, "dur": 81.395, + "args": { + "External id": 1423586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 11489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536504713.215, "dur": 2.088, + "args": { + "External id": 1423587,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11490, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536504808.547, "dur": 2089.196, + "args": { + "External id": 1423588,"Sequence number": 15109075, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11491 + } + }, + { + "ph": "f", "id": 444, "pid": 2338710, "tid": 2379450, "ts": 6410536504808.547, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536504939.393, "dur": 164.532, + "args": { + "External id": 1423589,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 11492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536505161.106, "dur": 54.051, + "args": { + "External id": 1423590,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 11493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536505238.473, "dur": 66.614, + "args": { + "External id": 1423591,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 11494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536505317.062, "dur": 39.358, + "args": { + "External id": 1423592,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536505364.145, "dur": 37.306, + "args": { + "External id": 1423593,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536505409.471, "dur": 53.852, + "args": { + "External id": 1423594,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536505477.877, "dur": 35.435, + "args": { + "External id": 1423595,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536505548.898, "dur": 30.474, + "args": { + "External id": 1423596,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 11499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536505605.347, "dur": 32.418, + "args": { + "External id": 1423597,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536505662.589, "dur": 23.660, + "args": { + "External id": 1423598,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536505701.337, "dur": 16.080, + "args": { + "External id": 1423599,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536505730.070, "dur": 43.703, + "args": { + "External id": 1423600,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536505777.762, "dur": 38.642, + "args": { + "External id": 1423601,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536505867.687, "dur": 344.907, + "args": { + "External id": 1423602,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536505967.252, "dur": 7.809, + "args": { + "External id": 1423603,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536505977.517, "dur": 3.179, + "args": { + "External id": 1423604,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536505982.292, "dur": 2.626, + "args": { + "External id": 1423605,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536505985.943, "dur": 4.334, + "args": { + "External id": 1423606,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536506049.750, "dur": 5.578, + "args": { + "External id": 1423607,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536506051.752, "dur": 3.354, + "args": { + "External id": 1423608,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536506095.453, "dur": 39.967, + "args": { + "External id": 1423609,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536506102.852, "dur": 2.371, + "args": { + "External id": 1423610,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536506137.493, "dur": 2.420, + "args": { + "External id": 1423611,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536506138.832, "dur": 0.987, + "args": { + "External id": 1423612,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536506141.017, "dur": 15.792, + "args": { + "External id": 1423613,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536506142.929, "dur": 0.667, + "args": { + "External id": 1423614,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536506256.970, "dur": 34.099, + "args": { + "External id": 1423615,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536506310.612, "dur": 17.581, + "args": { + "External id": 1423616,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536506338.531, "dur": 61.313, + "args": { + "External id": 1423617,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536506409.079, "dur": 68.071, + "args": { + "External id": 1423618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536506493.864, "dur": 27.864, + "args": { + "External id": 1423619,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536506530.109, "dur": 36.509, + "args": { + "External id": 1423620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536506576.641, "dur": 33.118, + "args": { + "External id": 1423621,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536506618.060, "dur": 37.237, + "args": { + "External id": 1423622,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536506678.721, "dur": 29.665, + "args": { + "External id": 1423623,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536506726.609, "dur": 27.654, + "args": { + "External id": 1423624,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536506772.864, "dur": 22.913, + "args": { + "External id": 1423625,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536506809.999, "dur": 18.193, + "args": { + "External id": 1423626,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536506842.694, "dur": 18.067, + "args": { + "External id": 1423627,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506948.540, "dur": 18.374, + "args": { + "External id": 1423628,"Record function id": 0, "Ev Idx": 11531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506953.013, "dur": 12.674, + "args": { + "External id": 1423629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536506957.937, "dur": 6.744, + "args": { + "External id": 1423630,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536506960.144, "dur": 4.383, + "args": { + "External id": 1423631,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506971.787, "dur": 5.750, + "args": { + "External id": 1423632,"Record function id": 0, "Ev Idx": 11535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506973.693, "dur": 3.308, + "args": { + "External id": 1423633,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536506974.447, "dur": 1.999, + "args": { + "External id": 1423634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536506975.072, "dur": 1.258, + "args": { + "External id": 1423635,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506981.320, "dur": 5.378, + "args": { + "External id": 1423636,"Record function id": 0, "Ev Idx": 11539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506983.154, "dur": 3.068, + "args": { + "External id": 1423637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536506983.715, "dur": 1.868, + "args": { + "External id": 1423638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536506984.529, "dur": 0.966, + "args": { + "External id": 1423639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506990.411, "dur": 4.488, + "args": { + "External id": 1423640,"Record function id": 0, "Ev Idx": 11543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506991.462, "dur": 2.945, + "args": { + "External id": 1423641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536506992.307, "dur": 1.540, + "args": { + "External id": 1423642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536506992.814, "dur": 0.957, + "args": { + "External id": 1423643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506998.466, "dur": 4.875, + "args": { + "External id": 1423644,"Record function id": 0, "Ev Idx": 11547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536506999.998, "dur": 2.856, + "args": { + "External id": 1423645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507000.629, "dur": 1.561, + "args": { + "External id": 1423646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507001.092, "dur": 1.022, + "args": { + "External id": 1423647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536507006.922, "dur": 7.175, + "args": { + "External id": 1423648,"Record function id": 0, "Ev Idx": 11551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536507008.261, "dur": 5.295, + "args": { + "External id": 1423649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507008.893, "dur": 4.056, + "args": { + "External id": 1423650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507009.254, "dur": 3.613, + "args": { + "External id": 1423651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536507017.876, "dur": 4.827, + "args": { + "External id": 1423652,"Record function id": 0, "Ev Idx": 11555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536507019.542, "dur": 2.705, + "args": { + "External id": 1423653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507020.256, "dur": 1.482, + "args": { + "External id": 1423654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507020.603, "dur": 1.025, + "args": { + "External id": 1423655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536507026.632, "dur": 4.976, + "args": { + "External id": 1423656,"Record function id": 0, "Ev Idx": 11559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536507028.235, "dur": 2.848, + "args": { + "External id": 1423657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507028.897, "dur": 1.631, + "args": { + "External id": 1423658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507029.642, "dur": 0.749, + "args": { + "External id": 1423659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536507035.349, "dur": 4.479, + "args": { + "External id": 1423660,"Record function id": 0, "Ev Idx": 11563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536507036.657, "dur": 2.707, + "args": { + "External id": 1423661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507037.188, "dur": 1.655, + "args": { + "External id": 1423662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536507037.694, "dur": 1.005, + "args": { + "External id": 1423663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536507044.449, "dur": 60504.923, + "args": { + "External id": 1423664,"Record function id": 0, "Sequence number": 15109074, "Fwd thread id": 1, "Ev Idx": 11567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536507046.068, "dur": 60492.008, + "args": { + "External id": 1423665,"Sequence number": 15109074, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11568 + } + }, + { + "ph": "f", "id": 445, "pid": 2338710, "tid": 2379450, "ts": 6410536507046.068, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410536507122.534, "dur": 45.549, + "args": { + "External id": 1423666,"Record function id": 0, "Ev Idx": 11569 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410536507177.672, "dur": 79.078, + "args": { + "External id": 1423667,"Record function id": 0, "Ev Idx": 11570 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 2338710, "tid": 2379450, + "ts": 6410536507264.180, "dur": 60264.327, + "args": { + "External id": 1423668,"Record function id": 0, "Ev Idx": 11571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536507369.756, "dur": 9.041, + "args": { + "External id": 1423669,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536507390.681, "dur": 5.610, + "args": { + "External id": 1423670,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536507412.358, "dur": 58981.356, + "args": { + "External id": 1423671,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536507447.328, "dur": 58930.784, + "args": { + "External id": 1423672,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536507584.366, "dur": 28.709, + "args": { + "External id": 1423673,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536507637.655, "dur": 58687.068, + "args": { + "External id": 1423674,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536507641.149, "dur": 58682.404, + "args": { + "External id": 1423675,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536507646.729, "dur": 13.580, + "args": { + "External id": 1423676,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536507662.726, "dur": 58656.556, + "args": { + "External id": 1423677,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536566534.009, "dur": 14.673, + "args": { + "External id": 1423678,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536566538.034, "dur": 9.963, + "args": { + "External id": 1423679,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536566585.254, "dur": 424.911, + "args": { + "External id": 1423680,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536566619.628, "dur": 384.274, + "args": { + "External id": 1423681,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11584, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536566633.641, "dur": 364.377, + "args": { + "External id": 1423682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536567032.866, "dur": 2.820, + "args": { + "External id": 1423683,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11586, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567148.832, "dur": 8.368, + "args": { + "External id": 1423684,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567173.552, "dur": 44.206, + "args": { + "External id": 1423685,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567230.101, "dur": 2.195, + "args": { + "External id": 1423686,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567245.412, "dur": 15.339, + "args": { + "External id": 1423687,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567268.202, "dur": 1.207, + "args": { + "External id": 1423688,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567274.072, "dur": 12.312, + "args": { + "External id": 1423689,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567294.215, "dur": 3.565, + "args": { + "External id": 1423690,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567302.272, "dur": 12.399, + "args": { + "External id": 1423691,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567320.114, "dur": 1.197, + "args": { + "External id": 1423692,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567325.495, "dur": 11.776, + "args": { + "External id": 1423693,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567342.104, "dur": 0.967, + "args": { + "External id": 1423694,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567347.563, "dur": 14.072, + "args": { + "External id": 1423695,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567368.485, "dur": 1.064, + "args": { + "External id": 1423696,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567373.620, "dur": 12.431, + "args": { + "External id": 1423697,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567390.879, "dur": 0.797, + "args": { + "External id": 1423698,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567396.228, "dur": 12.563, + "args": { + "External id": 1423699,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567428.493, "dur": 2.143, + "args": { + "External id": 1423700,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567437.668, "dur": 15.731, + "args": { + "External id": 1423701,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536567568.480, "dur": 2757.979, + "args": { + "External id": 1423702,"Record function id": 0, "Ev Idx": 11605 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410536567593.048, "dur": 570.943, + "args": { + "External id": 1423703,"Record function id": 0, "Ev Idx": 11606 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410536567612.059, "dur": 377.554, + "args": { + "External id": 1423704,"Record function id": 0, "Ev Idx": 11607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567714.219, "dur": 5.393, + "args": { + "External id": 1423705,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567723.964, "dur": 1.498, + "args": { + "External id": 1423706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567727.706, "dur": 3.631, + "args": { + "External id": 1423707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567733.593, "dur": 1.365, + "args": { + "External id": 1423708,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567739.637, "dur": 1.483, + "args": { + "External id": 1423709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567744.210, "dur": 0.996, + "args": { + "External id": 1423710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567747.234, "dur": 1.346, + "args": { + "External id": 1423711,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567750.639, "dur": 2.705, + "args": { + "External id": 1423712,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567755.126, "dur": 1.011, + "args": { + "External id": 1423713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536567759.601, "dur": 0.982, + "args": { + "External id": 1423714,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536567782.597, "dur": 170.290, + "args": { + "External id": 1423715,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536567802.140, "dur": 145.009, + "args": { + "External id": 1423716,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536567817.873, "dur": 20.100, + "args": { + "External id": 1423717,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536567842.967, "dur": 75.428, + "args": { + "External id": 1423718,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 11621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536567845.990, "dur": 71.959, + "args": { + "External id": 1423719,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 11622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536567850.337, "dur": 8.090, + "args": { + "External id": 1423720,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536567860.179, "dur": 56.960, + "args": { + "External id": 1423721,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 11624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536568174.946, "dur": 2123.592, + "args": { + "External id": 1423722,"Sequence number": 15109073, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11625 + } + }, + { + "ph": "f", "id": 446, "pid": 2338710, "tid": 2379450, "ts": 6410536568174.946, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536568314.960, "dur": 145.831, + "args": { + "External id": 1423723,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 11626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536568514.734, "dur": 48.083, + "args": { + "External id": 1423724,"kernel_hash": "cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/j7/cj7a47fzenagkzhlhxrxdlqstq7bg7zqy4egmin3jy4cjzfa2fi2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 11627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338710, "tid": 2379450, + "ts": 6410536568585.877, "dur": 62.679, + "args": { + "External id": 1423725,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 11628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536568663.922, "dur": 39.579, + "args": { + "External id": 1423726,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536568712.652, "dur": 38.998, + "args": { + "External id": 1423727,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536568761.435, "dur": 34.060, + "args": { + "External id": 1423728,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536568807.065, "dur": 35.640, + "args": { + "External id": 1423729,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536568870.833, "dur": 29.842, + "args": { + "External id": 1423730,"kernel_hash": "ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/t6/ct6pdrwin6gpbbhb3ubmfazw3qma3gzsewwbv4culi3mwmzponsp.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 11633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536568921.242, "dur": 32.390, + "args": { + "External id": 1423731,"kernel_hash": "cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/fh/cfha2kk6ylmk6fzcisr2hmw7gbvd62evmko6izxkbgo773kpqpv7.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536568978.233, "dur": 24.967, + "args": { + "External id": 1423732,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536569018.689, "dur": 18.814, + "args": { + "External id": 1423733,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536569049.390, "dur": 92.221, + "args": { + "External id": 1423734,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536569149.589, "dur": 40.304, + "args": { + "External id": 1423735,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338710, "tid": 2379450, + "ts": 6410536569226.747, "dur": 314.903, + "args": { + "External id": 1423736,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536569321.229, "dur": 7.535, + "args": { + "External id": 1423737,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536569331.271, "dur": 3.702, + "args": { + "External id": 1423738,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536569336.353, "dur": 2.744, + "args": { + "External id": 1423739,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536569340.204, "dur": 4.958, + "args": { + "External id": 1423740,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536569394.956, "dur": 5.578, + "args": { + "External id": 1423741,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536569396.939, "dur": 3.453, + "args": { + "External id": 1423742,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536569402.672, "dur": 56.872, + "args": { + "External id": 1423743,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536569409.363, "dur": 2.141, + "args": { + "External id": 1423744,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2379450, + "ts": 6410536569462.838, "dur": 2.842, + "args": { + "External id": 1423745,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536569464.314, "dur": 1.235, + "args": { + "External id": 1423746,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2379450, + "ts": 6410536569466.984, "dur": 18.323, + "args": { + "External id": 1423747,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536569470.650, "dur": 0.841, + "args": { + "External id": 1423748,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536569584.476, "dur": 34.741, + "args": { + "External id": 1423749,"kernel_hash": "cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/n3/cn3y2zipjjhfo3h2phytb3nb5ytxk4unc5shfjjsauycguastfpl.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536569639.412, "dur": 17.871, + "args": { + "External id": 1423750,"kernel_hash": "cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/c5/cc52kbqo4hhxyke6bamdvdcwi7wb5xue3fhqbjqsziegdnihxq3v.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536569667.257, "dur": 56.453, + "args": { + "External id": 1423751,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536569733.164, "dur": 46.958, + "args": { + "External id": 1423752,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536569792.623, "dur": 31.501, + "args": { + "External id": 1423753,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536569831.006, "dur": 40.440, + "args": { + "External id": 1423754,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536569878.747, "dur": 34.670, + "args": { + "External id": 1423755,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2379450, + "ts": 6410536569924.816, "dur": 34.988, + "args": { + "External id": 1423756,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338710, "tid": 2379450, + "ts": 6410536569984.880, "dur": 48.518, + "args": { + "External id": 1423757,"kernel_hash": "cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qs/cqsmoyietljwwem74pqj7rw77h2baol67y2jdqdgbsq7tblfkrf4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536570098.238, "dur": 35.524, + "args": { + "External id": 1423758,"kernel_hash": "cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/uk/cukcqlutgfm5qgp3jgdu3zjttoeb2ky7bgr2io5daf72hfzazg44.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536570155.320, "dur": 23.391, + "args": { + "External id": 1423759,"kernel_hash": "cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/yz/cyzcbvagv6sqe54tdiwtt2pobis2dvsgukvmbxe6inqo2qavtntb.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338710, "tid": 2379450, + "ts": 6410536570201.842, "dur": 18.794, + "args": { + "External id": 1423760,"kernel_hash": "cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/v5/cv5chmvmr3gn5d7eebb6pg3x4tnjvbuhdglamj3f65njpp45ulv6.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338710, "tid": 2379450, + "ts": 6410536570237.414, "dur": 20.500, + "args": { + "External id": 1423761,"kernel_hash": "cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/em/cemjdqi5ghk3i77b2rg37v3lyvjbugp7r7bobzjsarysugcnwrjj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570352.845, "dur": 19.466, + "args": { + "External id": 1423762,"Record function id": 0, "Ev Idx": 11665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570357.591, "dur": 13.495, + "args": { + "External id": 1423763,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570362.964, "dur": 7.061, + "args": { + "External id": 1423764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570364.916, "dur": 4.949, + "args": { + "External id": 1423765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570377.111, "dur": 6.660, + "args": { + "External id": 1423766,"Record function id": 0, "Ev Idx": 11669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570378.923, "dur": 4.212, + "args": { + "External id": 1423767,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570380.021, "dur": 2.479, + "args": { + "External id": 1423768,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570381.447, "dur": 0.962, + "args": { + "External id": 1423769,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570387.712, "dur": 6.081, + "args": { + "External id": 1423770,"Record function id": 0, "Ev Idx": 11673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570389.671, "dur": 3.624, + "args": { + "External id": 1423771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570390.569, "dur": 2.182, + "args": { + "External id": 1423772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570391.402, "dur": 1.262, + "args": { + "External id": 1423773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570397.801, "dur": 5.567, + "args": { + "External id": 1423774,"Record function id": 0, "Ev Idx": 11677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570399.631, "dur": 3.204, + "args": { + "External id": 1423775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570400.318, "dur": 1.933, + "args": { + "External id": 1423776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570400.866, "dur": 1.295, + "args": { + "External id": 1423777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570407.309, "dur": 5.426, + "args": { + "External id": 1423778,"Record function id": 0, "Ev Idx": 11681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570409.095, "dur": 3.099, + "args": { + "External id": 1423779,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570409.892, "dur": 1.393, + "args": { + "External id": 1423780,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570410.238, "dur": 0.957, + "args": { + "External id": 1423781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570435.045, "dur": 8.533, + "args": { + "External id": 1423782,"Record function id": 0, "Ev Idx": 11685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570437.524, "dur": 5.327, + "args": { + "External id": 1423783,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570438.903, "dur": 2.785, + "args": { + "External id": 1423784,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570439.612, "dur": 1.824, + "args": { + "External id": 1423785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570447.627, "dur": 7.931, + "args": { + "External id": 1423786,"Record function id": 0, "Ev Idx": 11689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570449.386, "dur": 5.669, + "args": { + "External id": 1423787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570450.167, "dur": 4.251, + "args": { + "External id": 1423788,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570451.105, "dur": 3.229, + "args": { + "External id": 1423789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570459.325, "dur": 5.900, + "args": { + "External id": 1423790,"Record function id": 0, "Ev Idx": 11693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570461.445, "dur": 3.220, + "args": { + "External id": 1423791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570462.083, "dur": 2.062, + "args": { + "External id": 1423792,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570462.751, "dur": 1.254, + "args": { + "External id": 1423793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570469.957, "dur": 5.461, + "args": { + "External id": 1423794,"Record function id": 0, "Ev Idx": 11697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536570471.645, "dur": 3.252, + "args": { + "External id": 1423795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570472.672, "dur": 1.670, + "args": { + "External id": 1423796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536570473.386, "dur": 0.815, + "args": { + "External id": 1423797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536570480.458, "dur": 61685.192, + "args": { + "External id": 1423798,"Record function id": 0, "Sequence number": 15109072, "Fwd thread id": 1, "Ev Idx": 11701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536570481.950, "dur": 61671.325, + "args": { + "External id": 1423799,"Sequence number": 15109072, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11702 + } + }, + { + "ph": "f", "id": 447, "pid": 2338710, "tid": 2379450, "ts": 6410536570481.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410536570517.289, "dur": 45.021, + "args": { + "External id": 1423800,"Record function id": 0, "Ev Idx": 11703 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410536570571.729, "dur": 82.269, + "args": { + "External id": 1423801,"Record function id": 0, "Ev Idx": 11704 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 2338710, "tid": 2379450, + "ts": 6410536570662.131, "dur": 61481.300, + "args": { + "External id": 1423802,"Record function id": 0, "Ev Idx": 11705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536570772.001, "dur": 9.071, + "args": { + "External id": 1423803,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536570792.338, "dur": 5.999, + "args": { + "External id": 1423804,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536570814.947, "dur": 60135.867, + "args": { + "External id": 1423805,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536570831.479, "dur": 60103.550, + "args": { + "External id": 1423806,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536570944.365, "dur": 24.788, + "args": { + "External id": 1423807,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536570995.594, "dur": 59879.437, + "args": { + "External id": 1423808,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536570998.849, "dur": 59874.784, + "args": { + "External id": 1423809,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536571004.652, "dur": 15.132, + "args": { + "External id": 1423810,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536571022.292, "dur": 59844.048, + "args": { + "External id": 1423811,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536631137.423, "dur": 16.697, + "args": { + "External id": 1423812,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536631142.106, "dur": 11.351, + "args": { + "External id": 1423813,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631194.556, "dur": 448.054, + "args": { + "External id": 1423814,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536631227.398, "dur": 408.753, + "args": { + "External id": 1423815,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11718, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536631242.475, "dur": 386.738, + "args": { + "External id": 1423816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536631668.107, "dur": 3.013, + "args": { + "External id": 1423817,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11720, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536631747.104, "dur": 8.559, + "args": { + "External id": 1423818,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631772.148, "dur": 40.737, + "args": { + "External id": 1423819,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536631826.835, "dur": 2.080, + "args": { + "External id": 1423820,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631835.658, "dur": 17.137, + "args": { + "External id": 1423821,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536631860.190, "dur": 1.337, + "args": { + "External id": 1423822,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631866.195, "dur": 13.393, + "args": { + "External id": 1423823,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536631886.740, "dur": 3.053, + "args": { + "External id": 1423824,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631894.245, "dur": 15.210, + "args": { + "External id": 1423825,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536631915.057, "dur": 1.218, + "args": { + "External id": 1423826,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631920.349, "dur": 12.443, + "args": { + "External id": 1423827,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536631938.329, "dur": 1.258, + "args": { + "External id": 1423828,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631943.931, "dur": 13.832, + "args": { + "External id": 1423829,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536631962.822, "dur": 1.010, + "args": { + "External id": 1423830,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631967.755, "dur": 13.368, + "args": { + "External id": 1423831,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536631986.365, "dur": 1.154, + "args": { + "External id": 1423832,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536631992.773, "dur": 13.774, + "args": { + "External id": 1423833,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536632011.694, "dur": 0.946, + "args": { + "External id": 1423834,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536632017.366, "dur": 13.218, + "args": { + "External id": 1423835,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536632186.382, "dur": 352.365, + "args": { + "External id": 1423836,"Record function id": 0, "Sequence number": 15109071, "Fwd thread id": 1, "Ev Idx": 11739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338710, "tid": 2379450, + "ts": 6410536632190.216, "dur": 335.937, + "args": { + "External id": 1423837,"Sequence number": 15109071, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11740 + } + }, + { + "ph": "f", "id": 448, "pid": 2338710, "tid": 2379450, "ts": 6410536632190.216, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 2338710, "tid": 2379450, + "ts": 6410536632337.337, "dur": 48.146, + "args": { + "External id": 1423838,"kernel_hash": "ci46ycwqu4mevlefaywvsre33v5ki6y5q5evkfmt4t2fie5todnp", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/i4/ci46ycwqu4mevlefaywvsre33v5ki6y5q5evkfmt4t2fie5todnp.py", "kernel_backend": "triton", "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 11741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_1", "pid": 2338710, "tid": 2379450, + "ts": 6410536632405.022, "dur": 49.565, + "args": { + "External id": 1423839,"kernel_hash": "c4hfnruzhc7gtb7rldzmrokxpon7tcgieufpcwt6pxhd3syqv6zy", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/4h/c4hfnruzhc7gtb7rldzmrokxpon7tcgieufpcwt6pxhd3syqv6zy.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096, 4096], [32000, 4096], []], "Ev Idx": 11742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_2", "pid": 2338710, "tid": 2379450, + "ts": 6410536632480.347, "dur": 25.766, + "args": { + "External id": 1423840,"kernel_hash": "cagfbb4snc4nnt5qtlfe5j5npoahg3qjke5pbuljm6ouabijdwft", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/ag/cagfbb4snc4nnt5qtlfe5j5npoahg3qjke5pbuljm6ouabijdwft.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 11743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536632553.307, "dur": 19.760, + "args": { + "External id": 1423841,"Record function id": 0, "Ev Idx": 11744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338710, "tid": 2379450, + "ts": 6410536632557.544, "dur": 14.486, + "args": { + "External id": 1423842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 11745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536632562.116, "dur": 8.894, + "args": { + "External id": 1423843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 11746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2379450, + "ts": 6410536632564.312, "dur": 6.455, + "args": { + "External id": 1423844,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 11747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_post_backward_callback", "pid": 2338710, "tid": 2379450, + "ts": 6410536632600.173, "dur": 13175.456, + "args": { + "External id": 1423845,"Record function id": 0, "Ev Idx": 11748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 2338710, "tid": 2379450, + "ts": 6410536632624.550, "dur": 48.508, + "args": { + "External id": 1423846,"Record function id": 0, "Ev Idx": 11749 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 2338710, "tid": 2379450, + "ts": 6410536632681.553, "dur": 302.180, + "args": { + "External id": 1423847,"Record function id": 0, "Ev Idx": 11750 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 2338710, "tid": 2379450, + "ts": 6410536632991.299, "dur": 12480.792, + "args": { + "External id": 1423848,"Record function id": 0, "Ev Idx": 11751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536633177.181, "dur": 10.287, + "args": { + "External id": 1423849,"Record function id": 0, "Concrete Inputs": ["[1134596096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2379450, + "ts": 6410536633201.422, "dur": 6.373, + "args": { + "External id": 1423850,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1134596096], []], "Ev Idx": 11753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536633236.586, "dur": 10238.795, + "args": { + "External id": 1423851,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [141824512, 1]], "Input Dims": [[], [], [], [8, 141824512]], "Ev Idx": 11754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338710, "tid": 2379450, + "ts": 6410536633266.774, "dur": 10191.739, + "args": { + "External id": 1423852,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [141824512, 1]], "Input Dims": [[], [], [], [8, 141824512]], "Ev Idx": 11755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536633976.394, "dur": 27.806, + "args": { + "External id": 1423853,"Record function id": 0, "Concrete Inputs": ["[277237]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2379450, + "ts": 6410536634358.510, "dur": 9026.144, + "args": { + "External id": 1423854,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[277237], [], [], [], [], [], [], []], "Ev Idx": 11757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2379450, + "ts": 6410536634363.571, "dur": 9019.703, + "args": { + "External id": 1423855,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[277237], [], [], [], [], [], []], "Ev Idx": 11758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536634371.834, "dur": 17.729, + "args": { + "External id": 1423856,"Record function id": 0, "Concrete Inputs": ["[277237]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2379450, + "ts": 6410536634393.410, "dur": 8982.710, + "args": { + "External id": 1423857,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[277237], [277237], []], "Ev Idx": 11760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536643644.315, "dur": 13.792, + "args": { + "External id": 1423858,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1134596096], [], [], [], [], []], "Ev Idx": 11761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2379450, + "ts": 6410536643648.580, "dur": 9.010, + "args": { + "External id": 1423859,"Record function id": 0, "Concrete Inputs": ["[141824512]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338710, "tid": 2379450, + "ts": 6410536643693.608, "dur": 464.525, + "args": { + "External id": 1423860,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[141824512], [1134596096], [], [], [], []], "Ev Idx": 11763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536643723.928, "dur": 427.688, + "args": { + "External id": 1423861,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 141824512, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1134596096], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11764, "In msg nelems": 1134596096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338710, "tid": 2379450, + "ts": 6410536643737.029, "dur": 406.584, + "args": { + "External id": 1423862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1134596096]], "Ev Idx": 11765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2379450, + "ts": 6410536644182.442, "dur": 2.879, + "args": { + "External id": 1423863,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11766, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644255.345, "dur": 7.936, + "args": { + "External id": 1423864,"Record function id": 0, "Concrete Inputs": ["", "[4000, 4096]", "[4096, 1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644280.016, "dur": 37.260, + "args": { + "External id": 1423865,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4000, 4096], [4000, 4096], []], "Ev Idx": 11768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644329.903, "dur": 1.850, + "args": { + "External id": 1423866,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644338.578, "dur": 16.614, + "args": { + "External id": 1423867,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644362.396, "dur": 1.609, + "args": { + "External id": 1423868,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "16384512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644368.789, "dur": 14.042, + "args": { + "External id": 1423869,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644389.611, "dur": 1.407, + "args": { + "External id": 1423870,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "18481664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644395.777, "dur": 13.616, + "args": { + "External id": 1423871,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644431.518, "dur": 1.930, + "args": { + "External id": 1423872,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "19005952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644472.407, "dur": 19.000, + "args": { + "External id": 1423873,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644500.238, "dur": 3.443, + "args": { + "External id": 1423874,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "19530240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644510.343, "dur": 13.769, + "args": { + "External id": 1423875,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644529.891, "dur": 0.879, + "args": { + "External id": 1423876,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644535.423, "dur": 12.893, + "args": { + "External id": 1423877,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644553.436, "dur": 0.857, + "args": { + "External id": 1423878,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "21627904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644558.863, "dur": 14.107, + "args": { + "External id": 1423879,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644577.894, "dur": 1.210, + "args": { + "External id": 1423880,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "28967936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644583.792, "dur": 12.074, + "args": { + "External id": 1423881,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644602.334, "dur": 1.027, + "args": { + "External id": 1423882,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "36307968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644608.161, "dur": 12.026, + "args": { + "External id": 1423883,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644625.668, "dur": 1.102, + "args": { + "External id": 1423884,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644631.425, "dur": 11.261, + "args": { + "External id": 1423885,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644648.106, "dur": 1.146, + "args": { + "External id": 1423886,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "43648512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644654.401, "dur": 12.069, + "args": { + "External id": 1423887,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644671.750, "dur": 0.937, + "args": { + "External id": 1423888,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "45745664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644677.583, "dur": 11.850, + "args": { + "External id": 1423889,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644695.002, "dur": 3.121, + "args": { + "External id": 1423890,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "46269952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644702.579, "dur": 12.294, + "args": { + "External id": 1423891,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644720.790, "dur": 1.087, + "args": { + "External id": 1423892,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "46794240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644729.369, "dur": 12.688, + "args": { + "External id": 1423893,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644748.032, "dur": 1.074, + "args": { + "External id": 1423894,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644753.224, "dur": 13.846, + "args": { + "External id": 1423895,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644772.525, "dur": 0.961, + "args": { + "External id": 1423896,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "48891904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644778.206, "dur": 12.646, + "args": { + "External id": 1423897,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644796.526, "dur": 1.120, + "args": { + "External id": 1423898,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "56231936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644803.015, "dur": 14.384, + "args": { + "External id": 1423899,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644825.097, "dur": 1.055, + "args": { + "External id": 1423900,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "63571968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644831.121, "dur": 13.432, + "args": { + "External id": 1423901,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644850.685, "dur": 1.098, + "args": { + "External id": 1423902,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644856.463, "dur": 13.625, + "args": { + "External id": 1423903,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644875.480, "dur": 0.859, + "args": { + "External id": 1423904,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "70912512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644881.024, "dur": 12.744, + "args": { + "External id": 1423905,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644899.335, "dur": 2.896, + "args": { + "External id": 1423906,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "73009664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644907.470, "dur": 13.829, + "args": { + "External id": 1423907,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644926.910, "dur": 0.968, + "args": { + "External id": 1423908,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "73533952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644932.843, "dur": 13.644, + "args": { + "External id": 1423909,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644952.228, "dur": 0.973, + "args": { + "External id": 1423910,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "74058240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644957.429, "dur": 13.199, + "args": { + "External id": 1423911,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644975.830, "dur": 1.051, + "args": { + "External id": 1423912,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536644980.737, "dur": 12.819, + "args": { + "External id": 1423913,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536644998.644, "dur": 0.929, + "args": { + "External id": 1423914,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "76155904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645003.684, "dur": 13.766, + "args": { + "External id": 1423915,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645023.277, "dur": 1.026, + "args": { + "External id": 1423916,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "83495936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645028.677, "dur": 12.447, + "args": { + "External id": 1423917,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645046.732, "dur": 0.883, + "args": { + "External id": 1423918,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "90835968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645052.718, "dur": 50.154, + "args": { + "External id": 1423919,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645112.833, "dur": 1.670, + "args": { + "External id": 1423920,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645120.313, "dur": 12.405, + "args": { + "External id": 1423921,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645139.522, "dur": 3.069, + "args": { + "External id": 1423922,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "98176512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645148.110, "dur": 13.069, + "args": { + "External id": 1423923,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645167.569, "dur": 1.006, + "args": { + "External id": 1423924,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "100273664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645173.044, "dur": 11.507, + "args": { + "External id": 1423925,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645189.701, "dur": 0.994, + "args": { + "External id": 1423926,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "100797952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645196.611, "dur": 12.207, + "args": { + "External id": 1423927,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645213.978, "dur": 1.206, + "args": { + "External id": 1423928,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "101322240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645219.629, "dur": 13.241, + "args": { + "External id": 1423929,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645237.537, "dur": 0.980, + "args": { + "External id": 1423930,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645243.327, "dur": 14.294, + "args": { + "External id": 1423931,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645262.473, "dur": 0.880, + "args": { + "External id": 1423932,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "103419904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645268.751, "dur": 11.942, + "args": { + "External id": 1423933,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645287.078, "dur": 0.822, + "args": { + "External id": 1423934,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "110759936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645292.829, "dur": 12.406, + "args": { + "External id": 1423935,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645310.084, "dur": 0.920, + "args": { + "External id": 1423936,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "118099968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645316.089, "dur": 10.728, + "args": { + "External id": 1423937,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645332.043, "dur": 3.091, + "args": { + "External id": 1423938,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645339.866, "dur": 14.459, + "args": { + "External id": 1423939,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2379450, + "ts": 6410536645360.036, "dur": 1.273, + "args": { + "External id": 1423940,"Record function id": 0, "Concrete Inputs": ["", "[4000, 4096]", "[4096, 1]", "125440512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2379450, + "ts": 6410536645365.656, "dur": 12.779, + "args": { + "External id": 1423941,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4000, 4096], [4000, 4096], []], "Ev Idx": 11844 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "ProfilerStep#32255", "pid": 2338710, "tid": 2338710, + "ts": 6410530220814.590, "dur": 6454128.216, + "args": { + "External id": 1402881,"Record function id": 0, "Ev Idx": 11845 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 2338710, "tid": 2338710, + "ts": 6410530220849.813, "dur": 813.917, + "args": { + "External id": 1402882,"Record function id": 0, "Ev Idx": 11846 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 2338710, "tid": 2338710, + "ts": 6410530221733.482, "dur": 2348.704, + "args": { + "External id": 1402883,"Record function id": 0, "Ev Idx": 11847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530222902.569, "dur": 7.694, + "args": { + "External id": 1402884,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338710, "tid": 2338710, + "ts": 6410530222933.442, "dur": 6.164, + "args": { + "External id": 1402885,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 11849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530223491.248, "dur": 2.802, + "args": { + "External id": 1402886,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338710, "tid": 2338710, + "ts": 6410530223504.663, "dur": 2.938, + "args": { + "External id": 1402887,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 11851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530223952.935, "dur": 1.738, + "args": { + "External id": 1402888,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338710, "tid": 2338710, + "ts": 6410530223959.361, "dur": 2.075, + "args": { + "External id": 1402889,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 11853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530224551.766, "dur": 15.944, + "args": { + "External id": 1402890,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], []], "Ev Idx": 11854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530224561.202, "dur": 2.454, + "args": { + "External id": 1402891,"Record function id": 0, "Concrete Inputs": ["", "[8, 8192]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 11855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530224569.623, "dur": 4.223, + "args": { + "External id": 1402892,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], []], "Ev Idx": 11856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530224571.715, "dur": 1.056, + "args": { + "External id": 1402893,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 11857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530224599.386, "dur": 361.613, + "args": { + "External id": 1402894,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], [], []], "Ev Idx": 11858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530224606.876, "dur": 353.496, + "args": { + "External id": 1402895,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], []], "Ev Idx": 11859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530224617.249, "dur": 10.082, + "args": { + "External id": 1402896,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "[4096, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530224629.476, "dur": 329.986, + "args": { + "External id": 1402897,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 11861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530224638.763, "dur": 0.542, + "args": { + "External id": 1402898,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 11862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530224642.008, "dur": 6.155, + "args": { + "External id": 1402899,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[8192, 1], [4096, 1]], "Input Dims": [[8, 4096], [8, 4096]], "Ev Idx": 11863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338710, "tid": 2338710, + "ts": 6410530224644.399, "dur": 3.597, + "args": { + "External id": 1402900,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], []], "Input Dims": [[8, 4096], [], []], "Ev Idx": 11864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530224647.124, "dur": 0.610, + "args": { + "External id": 1402901,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 11865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410530224650.693, "dur": 133.082, + "args": { + "External id": 1402902,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 11866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410530224653.108, "dur": 130.431, + "args": { + "External id": 1402903,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 11867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530224655.623, "dur": 17.089, + "args": { + "External id": 1402904,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 11868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530224659.634, "dur": 12.586, + "args": { + "External id": 1402905,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530224673.583, "dur": 109.560, + "args": { + "External id": 1402906,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 11870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530224785.578, "dur": 172.242, + "args": { + "External id": 1402907,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 11871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530224969.152, "dur": 413.159, + "args": { + "External id": 1402908,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], [], []], "Ev Idx": 11872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530224970.918, "dur": 410.726, + "args": { + "External id": 1402909,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], []], "Ev Idx": 11873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530224976.260, "dur": 5.712, + "args": { + "External id": 1402910,"Record function id": 0, "Concrete Inputs": ["[8, 8192]", "[8192, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530224985.918, "dur": 393.068, + "args": { + "External id": 1402911,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[8192, 1], [8192, 1], []], "Input Dims": [[8, 8192], [8, 8192], []], "Ev Idx": 11875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 2338710, "tid": 2338710, + "ts": 6410530225410.907, "dur": 75.372, + "args": { + "External id": 1402912,"Record function id": 0, "Concrete Inputs": ["0", "4096", "", "", "", "False"], "Input type": ["Scalar", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530225437.282, "dur": 4.987, + "args": { + "External id": 1402913,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 2338710, "tid": 2338710, + "ts": 6410530225444.914, "dur": 40.923, + "args": { + "External id": 1402914,"Record function id": 0, "Concrete Inputs": ["0", "4096", "1", ""], "Input type": ["Scalar", "Scalar", "Scalar", "long int"], "Input Strides": [[], [], [], [1]], "Input Dims": [[], [], [], [0]], "Ev Idx": 11878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410530225449.561, "dur": 7.875, + "args": { + "External id": 1402915,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["long int", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 11879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::repeat", "pid": 2338710, "tid": 2338710, + "ts": 6410530225498.018, "dur": 73.555, + "args": { + "External id": 1402916,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338710, "tid": 2338710, + "ts": 6410530225505.244, "dur": 7.422, + "args": { + "External id": 1402917,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[4096], [], []], "Ev Idx": 11881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530225510.525, "dur": 1.880, + "args": { + "External id": 1402918,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "[4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 11882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530225513.979, "dur": 3.237, + "args": { + "External id": 1402919,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410530225519.474, "dur": 4.210, + "args": { + "External id": 1402920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[4096, 1]], "Input Dims": [[8, 4096]], "Ev Idx": 11884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338710, "tid": 2338710, + "ts": 6410530225525.704, "dur": 5.079, + "args": { + "External id": 1402921,"Record function id": 0, "Concrete Inputs": ["", "0", "1", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 11885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530225529.860, "dur": 0.608, + "args": { + "External id": 1402922,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1]", "[4096, 1, 4096]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 11886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338710, "tid": 2338710, + "ts": 6410530225531.582, "dur": 5.216, + "args": { + "External id": 1402923,"Record function id": 0, "Concrete Inputs": ["", "1", "4096", "4096"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[8, 4096, 1], [], [], []], "Ev Idx": 11887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530225535.874, "dur": 0.839, + "args": { + "External id": 1402924,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "[4096, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[8, 4096, 1], [], [], []], "Ev Idx": 11888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530225538.808, "dur": 6.190, + "args": { + "External id": 1402925,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[4096, 1], [4096, 4096, 4096, 1]], "Input Dims": [[1, 4096], [8, 1, 1, 4096]], "Ev Idx": 11889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338710, "tid": 2338710, + "ts": 6410530225542.146, "dur": 2.744, + "args": { + "External id": 1402926,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1, 4096], [], []], "Ev Idx": 11890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530225543.975, "dur": 0.827, + "args": { + "External id": 1402927,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "[0, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 11891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530225546.246, "dur": 24.720, + "args": { + "External id": 1402928,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 4096, 4096, 1], [0, 4096, 4096, 1], []], "Input Dims": [[8, 1, 1, 4096], [8, 1, 1, 4096], []], "Ev Idx": 11892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530225579.804, "dur": 27.771, + "args": { + "External id": 1402929,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 11893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530225581.427, "dur": 25.904, + "args": { + "External id": 1402930,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], []], "Ev Idx": 11894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530225586.991, "dur": 2.794, + "args": { + "External id": 1402931,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "[4096, 1]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530225590.635, "dur": 16.239, + "args": { + "External id": 1402932,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 11896 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_pre_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530225720.039, "dur": 151.649, + "args": { + "External id": 1402933,"Record function id": 0, "Ev Idx": 11897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 2338710, "tid": 2338710, + "ts": 6410530225805.995, "dur": 54.824, + "args": { + "External id": 1402934,"Record function id": 0, "Ev Idx": 11898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530225879.294, "dur": 46.743, + "args": { + "External id": 1402935,"Record function id": 0, "Ev Idx": 11899 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530225935.104, "dur": 13823.514, + "args": { + "External id": 1402936,"Record function id": 0, "Ev Idx": 11900 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 2338710, "tid": 2338710, + "ts": 6410530225945.777, "dur": 1487.427, + "args": { + "External id": 1402937,"Record function id": 0, "Ev Idx": 11901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530226103.137, "dur": 9.289, + "args": { + "External id": 1402938,"Record function id": 0, "Concrete Inputs": ["[141824512]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530226131.335, "dur": 143.838, + "args": { + "External id": 1402939,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[141824512], [], []], "Ev Idx": 11903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226136.606, "dur": 1.695, + "args": { + "External id": 1402940,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226144.824, "dur": 0.431, + "args": { + "External id": 1402941,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226146.306, "dur": 0.480, + "args": { + "External id": 1402942,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "16384512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226147.450, "dur": 2.922, + "args": { + "External id": 1402943,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "18481664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226159.246, "dur": 0.551, + "args": { + "External id": 1402944,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19005952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226160.449, "dur": 0.250, + "args": { + "External id": 1402945,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "19530240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226161.522, "dur": 2.264, + "args": { + "External id": 1402946,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226167.050, "dur": 0.289, + "args": { + "External id": 1402947,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "21627904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226168.024, "dur": 0.504, + "args": { + "External id": 1402948,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "28967936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226174.057, "dur": 0.409, + "args": { + "External id": 1402949,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "36307968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226175.147, "dur": 0.312, + "args": { + "External id": 1402950,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226176.650, "dur": 2.443, + "args": { + "External id": 1402951,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "43648512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226183.916, "dur": 0.292, + "args": { + "External id": 1402952,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "45745664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226184.946, "dur": 0.261, + "args": { + "External id": 1402953,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "46269952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226185.876, "dur": 2.128, + "args": { + "External id": 1402954,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "46794240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226190.769, "dur": 0.319, + "args": { + "External id": 1402955,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226191.888, "dur": 0.384, + "args": { + "External id": 1402956,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "48891904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226197.544, "dur": 0.462, + "args": { + "External id": 1402957,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "56231936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226198.889, "dur": 0.324, + "args": { + "External id": 1402958,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "63571968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226200.159, "dur": 2.490, + "args": { + "External id": 1402959,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226207.391, "dur": 0.498, + "args": { + "External id": 1402960,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "70912512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226208.731, "dur": 0.398, + "args": { + "External id": 1402961,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73009664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226209.924, "dur": 2.036, + "args": { + "External id": 1402962,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73533952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226214.808, "dur": 0.341, + "args": { + "External id": 1402963,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "74058240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226215.973, "dur": 0.442, + "args": { + "External id": 1402964,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226222.026, "dur": 0.350, + "args": { + "External id": 1402965,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "76155904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226223.024, "dur": 0.291, + "args": { + "External id": 1402966,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "83495936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226224.233, "dur": 2.563, + "args": { + "External id": 1402967,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "90835968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226231.123, "dur": 0.384, + "args": { + "External id": 1402968,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226232.435, "dur": 0.444, + "args": { + "External id": 1402969,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "98176512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226233.585, "dur": 2.227, + "args": { + "External id": 1402970,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100273664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226238.822, "dur": 0.397, + "args": { + "External id": 1402971,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100797952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226239.898, "dur": 0.261, + "args": { + "External id": 1402972,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "101322240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226245.011, "dur": 0.308, + "args": { + "External id": 1402973,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226245.993, "dur": 0.355, + "args": { + "External id": 1402974,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "103419904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226247.253, "dur": 2.941, + "args": { + "External id": 1402975,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "110759936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226255.234, "dur": 0.307, + "args": { + "External id": 1402976,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "118099968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226256.042, "dur": 0.349, + "args": { + "External id": 1402977,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226257.113, "dur": 2.373, + "args": { + "External id": 1402978,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "125440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530226301.260, "dur": 162.900, + "args": { + "External id": 1402979,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530226539.973, "dur": 320.008, + "args": { + "External id": 1402980,"Record function id": 0, "Concrete Inputs": ["", "", "141824512", "8", "4", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530226557.347, "dur": 5.273, + "args": { + "External id": 1402981,"Record function id": 0, "Concrete Inputs": ["[1134596096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530226569.835, "dur": 14.757, + "args": { + "External id": 1402982,"Record function id": 0, "Concrete Inputs": ["", "0", "567298048", "141824512"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1134596096], [], [], []], "Ev Idx": 11946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530226574.367, "dur": 9.849, + "args": { + "External id": 1402983,"Record function id": 0, "Concrete Inputs": ["", "0", "567298048", "709122560", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[1134596096], [], [], [], []], "Ev Idx": 11947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226580.467, "dur": 0.900, + "args": { + "External id": 1402984,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "[1]", "567298048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1134596096], [], [], []], "Ev Idx": 11948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530226593.087, "dur": 113.053, + "args": { + "External id": 1402985,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[141824512], [], []], "Ev Idx": 11949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226595.069, "dur": 0.732, + "args": { + "External id": 1402986,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "567298048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226597.416, "dur": 0.504, + "args": { + "External id": 1402987,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "583682048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226601.493, "dur": 2.432, + "args": { + "External id": 1402988,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "583682560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226604.657, "dur": 1.051, + "args": { + "External id": 1402989,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "585779712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226608.928, "dur": 0.706, + "args": { + "External id": 1402990,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "586304000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226610.546, "dur": 0.470, + "args": { + "External id": 1402991,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "586828288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226612.117, "dur": 0.516, + "args": { + "External id": 1402992,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "588925440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226616.174, "dur": 0.377, + "args": { + "External id": 1402993,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "588925952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226617.041, "dur": 0.956, + "args": { + "External id": 1402994,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "596265984"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226618.705, "dur": 0.317, + "args": { + "External id": 1402995,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "603606016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226621.584, "dur": 2.448, + "args": { + "External id": 1402996,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "610946048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226624.876, "dur": 0.455, + "args": { + "External id": 1402997,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "610946560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226627.693, "dur": 2.534, + "args": { + "External id": 1402998,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "613043712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226630.987, "dur": 0.518, + "args": { + "External id": 1402999,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "613568000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226632.153, "dur": 0.652, + "args": { + "External id": 1403000,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "614092288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226637.784, "dur": 0.337, + "args": { + "External id": 1403001,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "616189440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226638.607, "dur": 0.264, + "args": { + "External id": 1403002,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "616189952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226639.644, "dur": 0.307, + "args": { + "External id": 1403003,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "623529984"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226644.100, "dur": 2.507, + "args": { + "External id": 1403004,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "630870016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226647.058, "dur": 0.303, + "args": { + "External id": 1403005,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "638210048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226649.597, "dur": 2.239, + "args": { + "External id": 1403006,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "638210560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226652.633, "dur": 0.311, + "args": { + "External id": 1403007,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "640307712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226653.420, "dur": 0.316, + "args": { + "External id": 1403008,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "640832000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226658.955, "dur": 0.401, + "args": { + "External id": 1403009,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "641356288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226660.118, "dur": 0.383, + "args": { + "External id": 1403010,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "643453440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226661.324, "dur": 0.302, + "args": { + "External id": 1403011,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "643453952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226666.197, "dur": 2.306, + "args": { + "External id": 1403012,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "650793984"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226669.224, "dur": 0.356, + "args": { + "External id": 1403013,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "658134016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226672.299, "dur": 1.388, + "args": { + "External id": 1403014,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "665474048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226674.267, "dur": 0.433, + "args": { + "External id": 1403015,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "665474560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226675.357, "dur": 0.280, + "args": { + "External id": 1403016,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "667571712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226679.220, "dur": 0.244, + "args": { + "External id": 1403017,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "668096000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226680.017, "dur": 0.339, + "args": { + "External id": 1403018,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "668620288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226680.862, "dur": 0.375, + "args": { + "External id": 1403019,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "670717440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226684.855, "dur": 1.797, + "args": { + "External id": 1403020,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "670717952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226687.631, "dur": 0.371, + "args": { + "External id": 1403021,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "678057984"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226690.347, "dur": 1.756, + "args": { + "External id": 1403022,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "685398016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226692.913, "dur": 0.254, + "args": { + "External id": 1403023,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "692738048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530226693.751, "dur": 0.257, + "args": { + "External id": 1403024,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "692738560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530226726.268, "dur": 118.743, + "args": { + "External id": 1403025,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530226922.437, "dur": 374.624, + "args": { + "External id": 1403026,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[1134596096], [141824512], [], [], []], "Ev Idx": 11990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530226959.382, "dur": 331.866, + "args": { + "External id": 1403027,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1134596096, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[141824512], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11991, "In msg nelems": 141824512 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530226969.521, "dur": 316.053, + "args": { + "External id": 1403028,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[141824512]], "Ev Idx": 11992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530227327.183, "dur": 2.380, + "args": { + "External id": 1403029,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11993, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 2338710, "tid": 2338710, + "ts": 6410530227451.563, "dur": 12088.657, + "args": { + "External id": 1403030,"Record function id": 0, "Ev Idx": 11994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227674.518, "dur": 7.117, + "args": { + "External id": 1403031,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1134596096], []], "Ev Idx": 11995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227685.657, "dur": 1.608, + "args": { + "External id": 1403032,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[131072000], []], "Ev Idx": 11996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227689.258, "dur": 0.986, + "args": { + "External id": 1403033,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227691.944, "dur": 3.458, + "args": { + "External id": 1403034,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227696.707, "dur": 1.039, + "args": { + "External id": 1403035,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227699.251, "dur": 0.975, + "args": { + "External id": 1403036,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227704.195, "dur": 1.126, + "args": { + "External id": 1403037,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227706.533, "dur": 2.440, + "args": { + "External id": 1403038,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227712.433, "dur": 1.077, + "args": { + "External id": 1403039,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227714.923, "dur": 0.966, + "args": { + "External id": 1403040,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227720.147, "dur": 0.938, + "args": { + "External id": 1403041,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227722.295, "dur": 2.509, + "args": { + "External id": 1403042,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227726.120, "dur": 0.855, + "args": { + "External id": 1403043,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227728.102, "dur": 1.000, + "args": { + "External id": 1403044,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227732.860, "dur": 1.450, + "args": { + "External id": 1403045,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227735.435, "dur": 2.208, + "args": { + "External id": 1403046,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227741.346, "dur": 0.814, + "args": { + "External id": 1403047,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227743.328, "dur": 0.890, + "args": { + "External id": 1403048,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227747.770, "dur": 0.763, + "args": { + "External id": 1403049,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227750.027, "dur": 2.706, + "args": { + "External id": 1403050,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227753.822, "dur": 1.023, + "args": { + "External id": 1403051,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227756.013, "dur": 1.045, + "args": { + "External id": 1403052,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227760.541, "dur": 1.213, + "args": { + "External id": 1403053,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227762.963, "dur": 1.781, + "args": { + "External id": 1403054,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227785.934, "dur": 0.948, + "args": { + "External id": 1403055,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227788.633, "dur": 0.952, + "args": { + "External id": 1403056,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227792.787, "dur": 0.782, + "args": { + "External id": 1403057,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227794.724, "dur": 2.460, + "args": { + "External id": 1403058,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227798.247, "dur": 0.762, + "args": { + "External id": 1403059,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227800.109, "dur": 0.796, + "args": { + "External id": 1403060,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227804.033, "dur": 0.743, + "args": { + "External id": 1403061,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227805.756, "dur": 1.800, + "args": { + "External id": 1403062,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227810.906, "dur": 0.725, + "args": { + "External id": 1403063,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227812.738, "dur": 1.086, + "args": { + "External id": 1403064,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227817.458, "dur": 0.839, + "args": { + "External id": 1403065,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227819.492, "dur": 3.156, + "args": { + "External id": 1403066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227824.002, "dur": 0.877, + "args": { + "External id": 1403067,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227826.119, "dur": 0.973, + "args": { + "External id": 1403068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227830.628, "dur": 0.919, + "args": { + "External id": 1403069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530227832.791, "dur": 1.765, + "args": { + "External id": 1403070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[131072000], []], "Ev Idx": 12034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530227864.004, "dur": 11606.839, + "args": { + "External id": 1403071,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[141824512, 1], [], [], []], "Input Dims": [[8, 141824512], [], [], []], "Ev Idx": 12035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530227888.166, "dur": 11568.864, + "args": { + "External id": 1403072,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[141824512, 1], [], [], []], "Input Dims": [[8, 141824512], [], [], []], "Ev Idx": 12036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530227910.963, "dur": 5.347, + "args": { + "External id": 1403073,"Record function id": 0, "Concrete Inputs": ["[4384]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530227922.497, "dur": 11470.640, + "args": { + "External id": 1403074,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[4384], [], [], [], [], [], [], []], "Ev Idx": 12038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530227927.063, "dur": 11465.027, + "args": { + "External id": 1403075,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[4384], [], [], [], [], [], []], "Ev Idx": 12039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530227933.616, "dur": 6.133, + "args": { + "External id": 1403076,"Record function id": 0, "Concrete Inputs": ["[4384]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530227941.340, "dur": 11446.276, + "args": { + "External id": 1403077,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4384], [4384], []], "Ev Idx": 12041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530239834.781, "dur": 30.378, + "args": { + "External id": 1403078,"Record function id": 0, "Ev Idx": 12042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 2338710, "tid": 2338710, + "ts": 6410530239866.769, "dur": 277.325, + "args": { + "External id": 1403079,"Record function id": 0, "Ev Idx": 12043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530239907.554, "dur": 225.604, + "args": { + "External id": 1403080,"Sequence number": 15108842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "long int"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32000, 4096], [8, 4096]], "Ev Idx": 12044 + } + }, + { + "ph": "s", "id": 224, "pid": 2338710, "tid": 2338710, "ts": 6410530239907.554, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530239982.643, "dur": 53.086, + "args": { + "External id": 1403081,"kernel_hash": "cvykvfdpfag3zvgkkgm7dmy4omdmsmvjcopgv6veoygd3dudukzf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/vy/cvykvfdpfag3zvgkkgm7dmy4omdmsmvjcopgv6veoygd3dudukzf.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096], [32000, 4096], [8, 4096, 4096], []], "Ev Idx": 12045 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530240216.659, "dur": 59.433, + "args": { + "External id": 1403082,"Record function id": 0, "Ev Idx": 12046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 2338710, "tid": 2338710, + "ts": 6410530240288.193, "dur": 8693.195, + "args": { + "External id": 1403083,"Record function id": 0, "Ev Idx": 12047 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338710, "tid": 2338710, + "ts": 6410530240297.896, "dur": 683.359, + "args": { + "External id": 1403084,"Record function id": 0, "Ev Idx": 12048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530240380.548, "dur": 14.039, + "args": { + "External id": 1403085,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530240409.211, "dur": 59.891, + "args": { + "External id": 1403086,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240435.557, "dur": 2.863, + "args": { + "External id": 1403087,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240440.495, "dur": 0.549, + "args": { + "External id": 1403088,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240441.690, "dur": 1.617, + "args": { + "External id": 1403089,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240446.700, "dur": 0.646, + "args": { + "External id": 1403090,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240447.906, "dur": 0.430, + "args": { + "External id": 1403091,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240452.761, "dur": 0.373, + "args": { + "External id": 1403092,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240453.849, "dur": 0.581, + "args": { + "External id": 1403093,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240454.956, "dur": 2.548, + "args": { + "External id": 1403094,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240462.260, "dur": 0.487, + "args": { + "External id": 1403095,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530240480.447, "dur": 71.716, + "args": { + "External id": 1403096,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530240586.845, "dur": 131.625, + "args": { + "External id": 1403097,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530240599.377, "dur": 6.588, + "args": { + "External id": 1403098,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530240611.484, "dur": 12.054, + "args": { + "External id": 1403099,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530240616.167, "dur": 6.979, + "args": { + "External id": 1403100,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240621.213, "dur": 0.608, + "args": { + "External id": 1403101,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530240630.110, "dur": 29.611, + "args": { + "External id": 1403102,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240631.832, "dur": 0.614, + "args": { + "External id": 1403103,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240636.214, "dur": 0.595, + "args": { + "External id": 1403104,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240639.202, "dur": 0.324, + "args": { + "External id": 1403105,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240642.120, "dur": 0.300, + "args": { + "External id": 1403106,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240643.181, "dur": 3.727, + "args": { + "External id": 1403107,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240647.463, "dur": 0.319, + "args": { + "External id": 1403108,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240651.126, "dur": 0.367, + "args": { + "External id": 1403109,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240654.019, "dur": 0.322, + "args": { + "External id": 1403110,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530240655.070, "dur": 0.287, + "args": { + "External id": 1403111,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530240672.407, "dur": 36.572, + "args": { + "External id": 1403112,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530240775.378, "dur": 130.377, + "args": { + "External id": 1403113,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530240807.359, "dur": 94.590, + "args": { + "External id": 1403114,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12078, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530240817.169, "dur": 80.324, + "args": { + "External id": 1403115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530240925.561, "dur": 1.874, + "args": { + "External id": 1403116,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12080, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338710, "tid": 2338710, + "ts": 6410530240998.299, "dur": 7681.093, + "args": { + "External id": 1403117,"Record function id": 0, "Ev Idx": 12081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241138.142, "dur": 5.892, + "args": { + "External id": 1403118,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241147.542, "dur": 1.471, + "args": { + "External id": 1403119,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241150.731, "dur": 0.924, + "args": { + "External id": 1403120,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241153.451, "dur": 3.178, + "args": { + "External id": 1403121,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241159.788, "dur": 1.168, + "args": { + "External id": 1403122,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241162.190, "dur": 1.054, + "args": { + "External id": 1403123,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241164.836, "dur": 0.927, + "args": { + "External id": 1403124,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241169.404, "dur": 1.872, + "args": { + "External id": 1403125,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241174.802, "dur": 0.973, + "args": { + "External id": 1403126,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530241177.152, "dur": 1.187, + "args": { + "External id": 1403127,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530241195.407, "dur": 7402.756, + "args": { + "External id": 1403128,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530241211.488, "dur": 7370.535, + "args": { + "External id": 1403129,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530241233.948, "dur": 14.549, + "args": { + "External id": 1403130,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530241254.629, "dur": 7264.352, + "args": { + "External id": 1403131,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530241258.976, "dur": 7258.553, + "args": { + "External id": 1403132,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530241264.180, "dur": 6.566, + "args": { + "External id": 1403133,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530241272.435, "dur": 7238.024, + "args": { + "External id": 1403134,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530248899.613, "dur": 46.684, + "args": { + "External id": 1403135,"Sequence number": 15108843, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12099 + } + }, + { + "ph": "s", "id": 223, "pid": 2338710, "tid": 2338710, "ts": 6410530248899.613, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530248923.332, "dur": 17.089, + "args": { + "External id": 1403136,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530248932.420, "dur": 7.601, + "args": { + "External id": 1403137,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530249032.399, "dur": 194.779, + "args": { + "External id": 1403138,"Record function id": 0, "Ev Idx": 12102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530249231.758, "dur": 1697.971, + "args": { + "External id": 1403139,"Record function id": 0, "Ev Idx": 12103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530249295.716, "dur": 1613.936, + "args": { + "External id": 1403140,"Sequence number": 15108844, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12104 + } + }, + { + "ph": "s", "id": 222, "pid": 2338710, "tid": 2338710, "ts": 6410530249295.716, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530249401.523, "dur": 119.645, + "args": { + "External id": 1403141,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530249548.940, "dur": 121.737, + "args": { + "External id": 1403142,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530249686.859, "dur": 53.104, + "args": { + "External id": 1403143,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530249752.431, "dur": 42.939, + "args": { + "External id": 1403144,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530249835.895, "dur": 36.534, + "args": { + "External id": 1403145,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530249905.285, "dur": 24.136, + "args": { + "External id": 1403146,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530249961.703, "dur": 248.709, + "args": { + "External id": 1403147,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530250030.217, "dur": 16.907, + "args": { + "External id": 1403148,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530250036.721, "dur": 9.191, + "args": { + "External id": 1403149,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530250050.179, "dur": 69.832, + "args": { + "External id": 1403150,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530250126.497, "dur": 1.865, + "args": { + "External id": 1403151,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530250131.754, "dur": 4.322, + "args": { + "External id": 1403152,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530250226.769, "dur": 84.209, + "args": { + "External id": 1403153,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530250361.961, "dur": 41.469, + "args": { + "External id": 1403154,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530250451.442, "dur": 74.206, + "args": { + "External id": 1403155,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530250542.347, "dur": 48.869, + "args": { + "External id": 1403156,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530250622.627, "dur": 37.380, + "args": { + "External id": 1403157,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530250671.430, "dur": 59.332, + "args": { + "External id": 1403158,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530250768.696, "dur": 32.415, + "args": { + "External id": 1403159,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12123 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.0)", "pid": 2338710, "tid": 2338710, + "ts": 6410530251015.174, "dur": 178.794, + "args": { + "External id": 1403160,"Record function id": 0, "Ev Idx": 12124 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530251289.936, "dur": 61.701, + "args": { + "External id": 1403161,"Record function id": 0, "Ev Idx": 12125 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 2338710, "tid": 2338710, + "ts": 6410530251363.483, "dur": 27301.267, + "args": { + "External id": 1403162,"Record function id": 0, "Ev Idx": 12126 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338710, "tid": 2338710, + "ts": 6410530251377.905, "dur": 1337.868, + "args": { + "External id": 1403163,"Record function id": 0, "Ev Idx": 12127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530251523.003, "dur": 14.267, + "args": { + "External id": 1403164,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530251555.887, "dur": 56.122, + "args": { + "External id": 1403165,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251565.102, "dur": 5.184, + "args": { + "External id": 1403166,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251574.147, "dur": 0.797, + "args": { + "External id": 1403167,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251578.532, "dur": 0.902, + "args": { + "External id": 1403168,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251582.274, "dur": 0.932, + "args": { + "External id": 1403169,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251584.683, "dur": 3.057, + "args": { + "External id": 1403170,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251592.145, "dur": 0.964, + "args": { + "External id": 1403171,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251595.790, "dur": 0.686, + "args": { + "External id": 1403172,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251597.813, "dur": 0.635, + "args": { + "External id": 1403173,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251601.921, "dur": 2.095, + "args": { + "External id": 1403174,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530251627.239, "dur": 89.457, + "args": { + "External id": 1403175,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530251770.599, "dur": 194.984, + "args": { + "External id": 1403176,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530251792.835, "dur": 8.167, + "args": { + "External id": 1403177,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530251808.483, "dur": 13.636, + "args": { + "External id": 1403178,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530251814.343, "dur": 7.232, + "args": { + "External id": 1403179,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251818.575, "dur": 1.190, + "args": { + "External id": 1403180,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530251832.963, "dur": 39.899, + "args": { + "External id": 1403181,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251837.582, "dur": 0.626, + "args": { + "External id": 1403182,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251840.003, "dur": 2.919, + "args": { + "External id": 1403183,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251844.416, "dur": 2.046, + "args": { + "External id": 1403184,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251850.210, "dur": 0.508, + "args": { + "External id": 1403185,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251851.847, "dur": 0.426, + "args": { + "External id": 1403186,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251855.569, "dur": 0.647, + "args": { + "External id": 1403187,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251859.629, "dur": 0.517, + "args": { + "External id": 1403188,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251861.229, "dur": 0.377, + "args": { + "External id": 1403189,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530251867.103, "dur": 0.369, + "args": { + "External id": 1403190,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530251892.023, "dur": 57.419, + "args": { + "External id": 1403191,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530252045.743, "dur": 536.097, + "args": { + "External id": 1403192,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530252154.076, "dur": 420.041, + "args": { + "External id": 1403193,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12157, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530252168.630, "dur": 397.021, + "args": { + "External id": 1403194,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530252612.730, "dur": 3.234, + "args": { + "External id": 1403195,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12159, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338710, "tid": 2338710, + "ts": 6410530252745.078, "dur": 25625.642, + "args": { + "External id": 1403196,"Record function id": 0, "Ev Idx": 12160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252886.631, "dur": 7.696, + "args": { + "External id": 1403197,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252899.166, "dur": 1.765, + "args": { + "External id": 1403198,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252903.736, "dur": 1.453, + "args": { + "External id": 1403199,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252907.743, "dur": 1.402, + "args": { + "External id": 1403200,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252911.343, "dur": 1.532, + "args": { + "External id": 1403201,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252917.449, "dur": 1.513, + "args": { + "External id": 1403202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252924.110, "dur": 1.427, + "args": { + "External id": 1403203,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252927.724, "dur": 4.375, + "args": { + "External id": 1403204,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252934.158, "dur": 1.415, + "args": { + "External id": 1403205,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530252939.751, "dur": 1.210, + "args": { + "External id": 1403206,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530252963.738, "dur": 25330.126, + "args": { + "External id": 1403207,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530252985.420, "dur": 25292.708, + "args": { + "External id": 1403208,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530253017.166, "dur": 17.558, + "args": { + "External id": 1403209,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530253039.851, "dur": 25176.884, + "args": { + "External id": 1403210,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530253043.113, "dur": 25172.301, + "args": { + "External id": 1403211,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530253049.667, "dur": 58.354, + "args": { + "External id": 1403212,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530253111.229, "dur": 25097.464, + "args": { + "External id": 1403213,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530278585.337, "dur": 44.005, + "args": { + "External id": 1403214,"Sequence number": 15108845, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12178 + } + }, + { + "ph": "s", "id": 221, "pid": 2338710, "tid": 2338710, "ts": 6410530278585.337, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530278607.182, "dur": 16.120, + "args": { + "External id": 1403215,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530278614.932, "dur": 7.778, + "args": { + "External id": 1403216,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530278714.347, "dur": 96.337, + "args": { + "External id": 1403217,"Record function id": 0, "Ev Idx": 12181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530278813.456, "dur": 1660.409, + "args": { + "External id": 1403218,"Record function id": 0, "Ev Idx": 12182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530278865.846, "dur": 1585.502, + "args": { + "External id": 1403219,"Sequence number": 15108846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12183 + } + }, + { + "ph": "s", "id": 220, "pid": 2338710, "tid": 2338710, "ts": 6410530278865.846, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530278970.971, "dur": 64.817, + "args": { + "External id": 1403220,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530279101.210, "dur": 120.633, + "args": { + "External id": 1403221,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530279239.990, "dur": 51.393, + "args": { + "External id": 1403222,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530279300.547, "dur": 39.036, + "args": { + "External id": 1403223,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530279384.539, "dur": 53.510, + "args": { + "External id": 1403224,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530279471.249, "dur": 28.373, + "args": { + "External id": 1403225,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530279525.843, "dur": 174.346, + "args": { + "External id": 1403226,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530279590.630, "dur": 18.614, + "args": { + "External id": 1403227,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530279597.188, "dur": 11.067, + "args": { + "External id": 1403228,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530279614.615, "dur": 5.909, + "args": { + "External id": 1403229,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530279622.330, "dur": 3.430, + "args": { + "External id": 1403230,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530279628.779, "dur": 4.545, + "args": { + "External id": 1403231,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530279717.330, "dur": 84.614, + "args": { + "External id": 1403232,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530279852.912, "dur": 40.252, + "args": { + "External id": 1403233,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530279908.823, "dur": 73.070, + "args": { + "External id": 1403234,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530279993.886, "dur": 55.478, + "args": { + "External id": 1403235,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530280134.698, "dur": 44.948, + "args": { + "External id": 1403236,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530280192.513, "dur": 79.163, + "args": { + "External id": 1403237,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530280305.306, "dur": 31.112, + "args": { + "External id": 1403238,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12202 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.1)", "pid": 2338710, "tid": 2338710, + "ts": 6410530280562.047, "dur": 101.818, + "args": { + "External id": 1403239,"Record function id": 0, "Ev Idx": 12203 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530280742.588, "dur": 48.965, + "args": { + "External id": 1403240,"Record function id": 0, "Ev Idx": 12204 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 2338710, "tid": 2338710, + "ts": 6410530280800.409, "dur": 26822.354, + "args": { + "External id": 1403241,"Record function id": 0, "Ev Idx": 12205 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338710, "tid": 2338710, + "ts": 6410530280812.802, "dur": 998.014, + "args": { + "External id": 1403242,"Record function id": 0, "Ev Idx": 12206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530280904.095, "dur": 10.748, + "args": { + "External id": 1403243,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530280929.767, "dur": 38.731, + "args": { + "External id": 1403244,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280935.200, "dur": 2.520, + "args": { + "External id": 1403245,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280941.473, "dur": 0.868, + "args": { + "External id": 1403246,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280945.449, "dur": 0.674, + "args": { + "External id": 1403247,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280946.910, "dur": 0.632, + "args": { + "External id": 1403248,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280949.874, "dur": 0.312, + "args": { + "External id": 1403249,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280953.417, "dur": 0.628, + "args": { + "External id": 1403250,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280954.886, "dur": 3.674, + "args": { + "External id": 1403251,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280960.848, "dur": 0.580, + "args": { + "External id": 1403252,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530280962.106, "dur": 0.541, + "args": { + "External id": 1403253,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530280979.048, "dur": 60.012, + "args": { + "External id": 1403254,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530281116.400, "dur": 136.170, + "args": { + "External id": 1403255,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530281131.304, "dur": 6.335, + "args": { + "External id": 1403256,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530281143.402, "dur": 10.990, + "args": { + "External id": 1403257,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530281148.093, "dur": 5.884, + "args": { + "External id": 1403258,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281151.528, "dur": 0.739, + "args": { + "External id": 1403259,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530281161.333, "dur": 33.566, + "args": { + "External id": 1403260,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281165.461, "dur": 2.275, + "args": { + "External id": 1403261,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281168.859, "dur": 0.554, + "args": { + "External id": 1403262,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281170.200, "dur": 0.568, + "args": { + "External id": 1403263,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281175.383, "dur": 2.254, + "args": { + "External id": 1403264,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281178.636, "dur": 0.344, + "args": { + "External id": 1403265,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281181.880, "dur": 0.418, + "args": { + "External id": 1403266,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281183.458, "dur": 0.363, + "args": { + "External id": 1403267,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281184.674, "dur": 0.479, + "args": { + "External id": 1403268,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530281188.553, "dur": 1.597, + "args": { + "External id": 1403269,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530281207.242, "dur": 36.741, + "args": { + "External id": 1403270,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530281310.505, "dur": 399.845, + "args": { + "External id": 1403271,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530281344.660, "dur": 360.454, + "args": { + "External id": 1403272,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12236, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530281356.176, "dur": 342.307, + "args": { + "External id": 1403273,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530281737.542, "dur": 2.279, + "args": { + "External id": 1403274,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12238, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338710, "tid": 2338710, + "ts": 6410530281831.918, "dur": 25559.730, + "args": { + "External id": 1403275,"Record function id": 0, "Ev Idx": 12239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281940.595, "dur": 6.597, + "args": { + "External id": 1403276,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281950.737, "dur": 1.571, + "args": { + "External id": 1403277,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281953.958, "dur": 4.081, + "args": { + "External id": 1403278,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281960.128, "dur": 0.990, + "args": { + "External id": 1403279,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281962.385, "dur": 1.391, + "args": { + "External id": 1403280,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281964.918, "dur": 0.799, + "args": { + "External id": 1403281,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281969.528, "dur": 0.691, + "args": { + "External id": 1403282,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281971.738, "dur": 2.328, + "args": { + "External id": 1403283,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281975.286, "dur": 0.873, + "args": { + "External id": 1403284,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530281977.742, "dur": 0.869, + "args": { + "External id": 1403285,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530282000.139, "dur": 25333.728, + "args": { + "External id": 1403286,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530282015.249, "dur": 25307.287, + "args": { + "External id": 1403287,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530282032.826, "dur": 16.020, + "args": { + "External id": 1403288,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530282052.348, "dur": 25230.510, + "args": { + "External id": 1403289,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530282054.993, "dur": 25226.827, + "args": { + "External id": 1403290,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530282096.810, "dur": 6.505, + "args": { + "External id": 1403291,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530282105.404, "dur": 25172.143, + "args": { + "External id": 1403292,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530307559.783, "dur": 36.308, + "args": { + "External id": 1403293,"Sequence number": 15108847, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12257 + } + }, + { + "ph": "s", "id": 219, "pid": 2338710, "tid": 2338710, "ts": 6410530307559.783, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530307579.967, "dur": 11.335, + "args": { + "External id": 1403294,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530307584.712, "dur": 6.260, + "args": { + "External id": 1403295,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530307663.072, "dur": 76.175, + "args": { + "External id": 1403296,"Record function id": 0, "Ev Idx": 12260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530307740.730, "dur": 1133.760, + "args": { + "External id": 1403297,"Record function id": 0, "Ev Idx": 12261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530307780.999, "dur": 1079.808, + "args": { + "External id": 1403298,"Sequence number": 15108848, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12262 + } + }, + { + "ph": "s", "id": 218, "pid": 2338710, "tid": 2338710, "ts": 6410530307780.999, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530307850.112, "dur": 50.175, + "args": { + "External id": 1403299,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530307913.112, "dur": 106.939, + "args": { + "External id": 1403300,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530308031.467, "dur": 77.165, + "args": { + "External id": 1403301,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530308122.166, "dur": 34.424, + "args": { + "External id": 1403302,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530308183.196, "dur": 26.633, + "args": { + "External id": 1403303,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530308229.000, "dur": 18.567, + "args": { + "External id": 1403304,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530308271.443, "dur": 132.906, + "args": { + "External id": 1403305,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530308320.224, "dur": 13.456, + "args": { + "External id": 1403306,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530308327.873, "dur": 4.880, + "args": { + "External id": 1403307,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530308336.384, "dur": 5.132, + "args": { + "External id": 1403308,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530308342.840, "dur": 1.437, + "args": { + "External id": 1403309,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530308346.829, "dur": 5.377, + "args": { + "External id": 1403310,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530308430.367, "dur": 57.286, + "args": { + "External id": 1403311,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530308525.270, "dur": 29.868, + "args": { + "External id": 1403312,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530308565.076, "dur": 42.908, + "args": { + "External id": 1403313,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530308616.520, "dur": 35.206, + "args": { + "External id": 1403314,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530308674.651, "dur": 25.897, + "args": { + "External id": 1403315,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530308709.030, "dur": 36.724, + "args": { + "External id": 1403316,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530308767.358, "dur": 18.017, + "args": { + "External id": 1403317,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.2)", "pid": 2338710, "tid": 2338710, + "ts": 6410530308939.947, "dur": 82.590, + "args": { + "External id": 1403318,"Record function id": 0, "Ev Idx": 12282 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530309141.498, "dur": 51.094, + "args": { + "External id": 1403319,"Record function id": 0, "Ev Idx": 12283 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 2338710, "tid": 2338710, + "ts": 6410530309202.705, "dur": 29188.359, + "args": { + "External id": 1403320,"Record function id": 0, "Ev Idx": 12284 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338710, "tid": 2338710, + "ts": 6410530309214.608, "dur": 1034.771, + "args": { + "External id": 1403321,"Record function id": 0, "Ev Idx": 12285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530309299.512, "dur": 10.950, + "args": { + "External id": 1403322,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530309323.913, "dur": 45.011, + "args": { + "External id": 1403323,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309329.525, "dur": 2.369, + "args": { + "External id": 1403324,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309338.502, "dur": 0.608, + "args": { + "External id": 1403325,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309339.896, "dur": 0.627, + "args": { + "External id": 1403326,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309345.803, "dur": 0.537, + "args": { + "External id": 1403327,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309351.366, "dur": 0.637, + "args": { + "External id": 1403328,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309352.874, "dur": 0.382, + "args": { + "External id": 1403329,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309355.769, "dur": 3.978, + "args": { + "External id": 1403330,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309360.562, "dur": 0.626, + "args": { + "External id": 1403331,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309361.744, "dur": 0.468, + "args": { + "External id": 1403332,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530309381.545, "dur": 77.542, + "args": { + "External id": 1403333,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530309498.533, "dur": 144.389, + "args": { + "External id": 1403334,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530309512.925, "dur": 5.081, + "args": { + "External id": 1403335,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530309523.206, "dur": 11.267, + "args": { + "External id": 1403336,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530309528.078, "dur": 6.008, + "args": { + "External id": 1403337,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309531.487, "dur": 0.647, + "args": { + "External id": 1403338,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530309542.905, "dur": 32.069, + "args": { + "External id": 1403339,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309544.331, "dur": 2.669, + "args": { + "External id": 1403340,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309548.098, "dur": 0.630, + "args": { + "External id": 1403341,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309551.978, "dur": 0.605, + "args": { + "External id": 1403342,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309555.512, "dur": 2.457, + "args": { + "External id": 1403343,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309560.404, "dur": 0.599, + "args": { + "External id": 1403344,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309561.630, "dur": 0.312, + "args": { + "External id": 1403345,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309564.171, "dur": 0.624, + "args": { + "External id": 1403346,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309567.780, "dur": 0.372, + "args": { + "External id": 1403347,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530309568.702, "dur": 2.159, + "args": { + "External id": 1403348,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530309596.076, "dur": 38.193, + "args": { + "External id": 1403349,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530309698.774, "dur": 441.675, + "args": { + "External id": 1403350,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530309735.821, "dur": 398.558, + "args": { + "External id": 1403351,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12315, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530309750.005, "dur": 377.592, + "args": { + "External id": 1403352,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530310169.716, "dur": 2.214, + "args": { + "External id": 1403353,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12317, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338710, "tid": 2338710, + "ts": 6410530310270.180, "dur": 27913.098, + "args": { + "External id": 1403354,"Record function id": 0, "Ev Idx": 12318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310383.497, "dur": 6.817, + "args": { + "External id": 1403355,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310393.698, "dur": 1.426, + "args": { + "External id": 1403356,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310396.937, "dur": 3.591, + "args": { + "External id": 1403357,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310402.155, "dur": 1.221, + "args": { + "External id": 1403358,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310404.682, "dur": 1.224, + "args": { + "External id": 1403359,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310407.031, "dur": 1.000, + "args": { + "External id": 1403360,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310411.871, "dur": 0.939, + "args": { + "External id": 1403361,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310414.462, "dur": 16.195, + "args": { + "External id": 1403362,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310434.498, "dur": 0.677, + "args": { + "External id": 1403363,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530310436.552, "dur": 0.812, + "args": { + "External id": 1403364,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530310459.696, "dur": 27672.270, + "args": { + "External id": 1403365,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530310476.185, "dur": 27646.189, + "args": { + "External id": 1403366,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530310496.792, "dur": 17.325, + "args": { + "External id": 1403367,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530310517.491, "dur": 27534.177, + "args": { + "External id": 1403368,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530310520.255, "dur": 27530.656, + "args": { + "External id": 1403369,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530310526.834, "dur": 6.874, + "args": { + "External id": 1403370,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530310535.368, "dur": 27511.784, + "args": { + "External id": 1403371,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530338331.978, "dur": 34.533, + "args": { + "External id": 1403372,"Sequence number": 15108849, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12336 + } + }, + { + "ph": "s", "id": 217, "pid": 2338710, "tid": 2338710, "ts": 6410530338331.978, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530338351.796, "dur": 9.956, + "args": { + "External id": 1403373,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530338356.242, "dur": 5.280, + "args": { + "External id": 1403374,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530338445.616, "dur": 73.752, + "args": { + "External id": 1403375,"Record function id": 0, "Ev Idx": 12339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530338523.411, "dur": 1196.183, + "args": { + "External id": 1403376,"Record function id": 0, "Ev Idx": 12340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530338564.804, "dur": 1139.710, + "args": { + "External id": 1403377,"Sequence number": 15108850, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12341 + } + }, + { + "ph": "s", "id": 216, "pid": 2338710, "tid": 2338710, "ts": 6410530338564.804, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530338635.786, "dur": 52.643, + "args": { + "External id": 1403378,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530338701.854, "dur": 101.517, + "args": { + "External id": 1403379,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530338818.019, "dur": 42.158, + "args": { + "External id": 1403380,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530338866.742, "dur": 30.159, + "args": { + "External id": 1403381,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530338926.631, "dur": 26.873, + "args": { + "External id": 1403382,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530338973.087, "dur": 18.856, + "args": { + "External id": 1403383,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530339014.156, "dur": 194.156, + "args": { + "External id": 1403384,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530339119.512, "dur": 13.089, + "args": { + "External id": 1403385,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530339124.722, "dur": 6.604, + "args": { + "External id": 1403386,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530339135.104, "dur": 4.117, + "args": { + "External id": 1403387,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530339140.807, "dur": 0.960, + "args": { + "External id": 1403388,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530339146.460, "dur": 4.917, + "args": { + "External id": 1403389,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530339221.080, "dur": 58.158, + "args": { + "External id": 1403390,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530339318.470, "dur": 33.005, + "args": { + "External id": 1403391,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530339361.665, "dur": 43.326, + "args": { + "External id": 1403392,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530339445.900, "dur": 41.671, + "args": { + "External id": 1403393,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530339521.474, "dur": 28.077, + "args": { + "External id": 1403394,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530339556.537, "dur": 36.235, + "args": { + "External id": 1403395,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530339611.108, "dur": 23.424, + "args": { + "External id": 1403396,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12360 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.3)", "pid": 2338710, "tid": 2338710, + "ts": 6410530339786.399, "dur": 82.665, + "args": { + "External id": 1403397,"Record function id": 0, "Ev Idx": 12361 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530339944.304, "dur": 47.949, + "args": { + "External id": 1403398,"Record function id": 0, "Ev Idx": 12362 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 2338710, "tid": 2338710, + "ts": 6410530340001.146, "dur": 29580.946, + "args": { + "External id": 1403399,"Record function id": 0, "Ev Idx": 12363 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338710, "tid": 2338710, + "ts": 6410530340010.992, "dur": 995.398, + "args": { + "External id": 1403400,"Record function id": 0, "Ev Idx": 12364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530340139.258, "dur": 10.068, + "args": { + "External id": 1403401,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530340162.451, "dur": 42.700, + "args": { + "External id": 1403402,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340170.266, "dur": 2.317, + "args": { + "External id": 1403403,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340176.650, "dur": 0.493, + "args": { + "External id": 1403404,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340177.877, "dur": 0.577, + "args": { + "External id": 1403405,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340181.949, "dur": 0.418, + "args": { + "External id": 1403406,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340185.366, "dur": 0.694, + "args": { + "External id": 1403407,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340188.715, "dur": 0.658, + "args": { + "External id": 1403408,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340190.085, "dur": 4.215, + "args": { + "External id": 1403409,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340195.144, "dur": 0.618, + "args": { + "External id": 1403410,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340198.608, "dur": 0.574, + "args": { + "External id": 1403411,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530340216.670, "dur": 56.396, + "args": { + "External id": 1403412,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530340306.726, "dur": 146.090, + "args": { + "External id": 1403413,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530340320.267, "dur": 4.463, + "args": { + "External id": 1403414,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530340329.708, "dur": 12.978, + "args": { + "External id": 1403415,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530340334.910, "dur": 7.378, + "args": { + "External id": 1403416,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340340.427, "dur": 0.619, + "args": { + "External id": 1403417,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530340349.025, "dur": 32.311, + "args": { + "External id": 1403418,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340351.076, "dur": 2.249, + "args": { + "External id": 1403419,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340356.248, "dur": 0.469, + "args": { + "External id": 1403420,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340357.257, "dur": 0.491, + "args": { + "External id": 1403421,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340363.249, "dur": 2.400, + "args": { + "External id": 1403422,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340366.242, "dur": 0.535, + "args": { + "External id": 1403423,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340367.809, "dur": 0.327, + "args": { + "External id": 1403424,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340371.343, "dur": 0.527, + "args": { + "External id": 1403425,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340372.802, "dur": 0.309, + "args": { + "External id": 1403426,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530340373.587, "dur": 2.932, + "args": { + "External id": 1403427,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530340393.843, "dur": 48.739, + "args": { + "External id": 1403428,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530340509.429, "dur": 403.081, + "args": { + "External id": 1403429,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530340546.264, "dur": 361.026, + "args": { + "External id": 1403430,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12394, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530340556.278, "dur": 343.257, + "args": { + "External id": 1403431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530340934.917, "dur": 2.433, + "args": { + "External id": 1403432,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12396, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338710, "tid": 2338710, + "ts": 6410530341026.236, "dur": 28344.376, + "args": { + "External id": 1403433,"Record function id": 0, "Ev Idx": 12397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341176.797, "dur": 7.074, + "args": { + "External id": 1403434,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341187.523, "dur": 1.078, + "args": { + "External id": 1403435,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341190.442, "dur": 3.522, + "args": { + "External id": 1403436,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341196.069, "dur": 0.935, + "args": { + "External id": 1403437,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341198.506, "dur": 1.047, + "args": { + "External id": 1403438,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341200.897, "dur": 0.775, + "args": { + "External id": 1403439,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341205.383, "dur": 0.976, + "args": { + "External id": 1403440,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341210.219, "dur": 2.816, + "args": { + "External id": 1403441,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341214.155, "dur": 1.187, + "args": { + "External id": 1403442,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530341216.604, "dur": 0.727, + "args": { + "External id": 1403443,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530341236.902, "dur": 28091.331, + "args": { + "External id": 1403444,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530341254.752, "dur": 28065.591, + "args": { + "External id": 1403445,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530341273.978, "dur": 17.110, + "args": { + "External id": 1403446,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530341294.444, "dur": 27988.176, + "args": { + "External id": 1403447,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530341297.300, "dur": 27984.772, + "args": { + "External id": 1403448,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530341303.211, "dur": 5.539, + "args": { + "External id": 1403449,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530341310.520, "dur": 27968.625, + "args": { + "External id": 1403450,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530369523.933, "dur": 31.695, + "args": { + "External id": 1403451,"Sequence number": 15108851, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12415 + } + }, + { + "ph": "s", "id": 215, "pid": 2338710, "tid": 2338710, "ts": 6410530369523.933, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530369539.964, "dur": 10.791, + "args": { + "External id": 1403452,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530369545.960, "dur": 4.440, + "args": { + "External id": 1403453,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530369621.539, "dur": 73.096, + "args": { + "External id": 1403454,"Record function id": 0, "Ev Idx": 12418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530369696.019, "dur": 1132.639, + "args": { + "External id": 1403455,"Record function id": 0, "Ev Idx": 12419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530369736.713, "dur": 1079.025, + "args": { + "External id": 1403456,"Sequence number": 15108852, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12420 + } + }, + { + "ph": "s", "id": 214, "pid": 2338710, "tid": 2338710, "ts": 6410530369736.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530369802.122, "dur": 50.688, + "args": { + "External id": 1403457,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530369865.273, "dur": 102.069, + "args": { + "External id": 1403458,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530369978.614, "dur": 38.286, + "args": { + "External id": 1403459,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530370025.350, "dur": 78.614, + "args": { + "External id": 1403460,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530370137.443, "dur": 31.904, + "args": { + "External id": 1403461,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530370190.874, "dur": 17.114, + "args": { + "External id": 1403462,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530370230.594, "dur": 134.557, + "args": { + "External id": 1403463,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530370279.577, "dur": 11.546, + "args": { + "External id": 1403464,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530370284.725, "dur": 5.742, + "args": { + "External id": 1403465,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530370293.432, "dur": 5.069, + "args": { + "External id": 1403466,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530370301.901, "dur": 1.222, + "args": { + "External id": 1403467,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530370305.362, "dur": 6.927, + "args": { + "External id": 1403468,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530370375.777, "dur": 70.426, + "args": { + "External id": 1403469,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530370481.383, "dur": 32.930, + "args": { + "External id": 1403470,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530370524.472, "dur": 46.023, + "args": { + "External id": 1403471,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530370578.151, "dur": 35.129, + "args": { + "External id": 1403472,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530370638.595, "dur": 25.368, + "args": { + "External id": 1403473,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530370671.931, "dur": 36.517, + "args": { + "External id": 1403474,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530370725.249, "dur": 19.725, + "args": { + "External id": 1403475,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12439 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.4)", "pid": 2338710, "tid": 2338710, + "ts": 6410530370893.745, "dur": 83.694, + "args": { + "External id": 1403476,"Record function id": 0, "Ev Idx": 12440 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530371088.302, "dur": 53.779, + "args": { + "External id": 1403477,"Record function id": 0, "Ev Idx": 12441 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 2338710, "tid": 2338710, + "ts": 6410530371152.696, "dur": 29283.429, + "args": { + "External id": 1403478,"Record function id": 0, "Ev Idx": 12442 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338710, "tid": 2338710, + "ts": 6410530371162.829, "dur": 1023.325, + "args": { + "External id": 1403479,"Record function id": 0, "Ev Idx": 12443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530371248.965, "dur": 10.421, + "args": { + "External id": 1403480,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530371272.916, "dur": 43.682, + "args": { + "External id": 1403481,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371281.283, "dur": 2.305, + "args": { + "External id": 1403482,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371287.246, "dur": 0.706, + "args": { + "External id": 1403483,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371290.959, "dur": 0.784, + "args": { + "External id": 1403484,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371292.577, "dur": 0.703, + "args": { + "External id": 1403485,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371295.476, "dur": 0.700, + "args": { + "External id": 1403486,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371299.029, "dur": 0.423, + "args": { + "External id": 1403487,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371300.054, "dur": 3.449, + "args": { + "External id": 1403488,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371304.046, "dur": 0.499, + "args": { + "External id": 1403489,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371307.399, "dur": 0.544, + "args": { + "External id": 1403490,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530371328.354, "dur": 56.466, + "args": { + "External id": 1403491,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530371436.479, "dur": 139.382, + "args": { + "External id": 1403492,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530371453.145, "dur": 5.603, + "args": { + "External id": 1403493,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530371464.024, "dur": 10.786, + "args": { + "External id": 1403494,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530371468.628, "dur": 5.769, + "args": { + "External id": 1403495,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371471.921, "dur": 0.772, + "args": { + "External id": 1403496,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530371481.973, "dur": 33.188, + "args": { + "External id": 1403497,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371485.562, "dur": 2.004, + "args": { + "External id": 1403498,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371488.678, "dur": 0.568, + "args": { + "External id": 1403499,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371489.827, "dur": 0.501, + "args": { + "External id": 1403500,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371494.389, "dur": 2.482, + "args": { + "External id": 1403501,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371497.516, "dur": 0.554, + "args": { + "External id": 1403502,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371498.711, "dur": 0.365, + "args": { + "External id": 1403503,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371503.070, "dur": 0.403, + "args": { + "External id": 1403504,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371504.074, "dur": 0.496, + "args": { + "External id": 1403505,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530371507.308, "dur": 1.732, + "args": { + "External id": 1403506,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530371531.603, "dur": 35.429, + "args": { + "External id": 1403507,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530371633.091, "dur": 400.244, + "args": { + "External id": 1403508,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530371667.552, "dur": 360.141, + "args": { + "External id": 1403509,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12473, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530371677.983, "dur": 343.442, + "args": { + "External id": 1403510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530372103.211, "dur": 3.593, + "args": { + "External id": 1403511,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12475, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338710, "tid": 2338710, + "ts": 6410530372207.413, "dur": 28013.103, + "args": { + "External id": 1403512,"Record function id": 0, "Ev Idx": 12476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372315.042, "dur": 6.935, + "args": { + "External id": 1403513,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372325.231, "dur": 0.988, + "args": { + "External id": 1403514,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372327.964, "dur": 3.321, + "args": { + "External id": 1403515,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372332.784, "dur": 1.279, + "args": { + "External id": 1403516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372335.412, "dur": 0.833, + "args": { + "External id": 1403517,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372340.235, "dur": 1.310, + "args": { + "External id": 1403518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372345.124, "dur": 1.122, + "args": { + "External id": 1403519,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372347.866, "dur": 3.759, + "args": { + "External id": 1403520,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372352.918, "dur": 1.013, + "args": { + "External id": 1403521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530372357.443, "dur": 1.151, + "args": { + "External id": 1403522,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530372375.892, "dur": 27800.437, + "args": { + "External id": 1403523,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530372401.179, "dur": 27766.941, + "args": { + "External id": 1403524,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530372431.544, "dur": 17.146, + "args": { + "External id": 1403525,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530372452.537, "dur": 27679.779, + "args": { + "External id": 1403526,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530372454.883, "dur": 27676.900, + "args": { + "External id": 1403527,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530372460.495, "dur": 5.473, + "args": { + "External id": 1403528,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530372467.796, "dur": 27660.669, + "args": { + "External id": 1403529,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530400363.414, "dur": 31.518, + "args": { + "External id": 1403530,"Sequence number": 15108853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12494 + } + }, + { + "ph": "s", "id": 213, "pid": 2338710, "tid": 2338710, "ts": 6410530400363.414, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530400378.861, "dur": 11.544, + "args": { + "External id": 1403531,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530400385.511, "dur": 4.662, + "args": { + "External id": 1403532,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530400476.478, "dur": 71.185, + "args": { + "External id": 1403533,"Record function id": 0, "Ev Idx": 12497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530400549.088, "dur": 1140.312, + "args": { + "External id": 1403534,"Record function id": 0, "Ev Idx": 12498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530400587.167, "dur": 1088.583, + "args": { + "External id": 1403535,"Sequence number": 15108854, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12499 + } + }, + { + "ph": "s", "id": 212, "pid": 2338710, "tid": 2338710, "ts": 6410530400587.167, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530400653.520, "dur": 49.209, + "args": { + "External id": 1403536,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530400715.101, "dur": 104.347, + "args": { + "External id": 1403537,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530400831.093, "dur": 44.382, + "args": { + "External id": 1403538,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530400884.737, "dur": 30.750, + "args": { + "External id": 1403539,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530400942.174, "dur": 25.383, + "args": { + "External id": 1403540,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530400986.097, "dur": 17.064, + "args": { + "External id": 1403541,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530401030.160, "dur": 186.855, + "args": { + "External id": 1403542,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530401130.956, "dur": 12.651, + "args": { + "External id": 1403543,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530401136.064, "dur": 6.601, + "args": { + "External id": 1403544,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530401147.661, "dur": 5.210, + "args": { + "External id": 1403545,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530401154.140, "dur": 1.000, + "args": { + "External id": 1403546,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530401157.527, "dur": 4.584, + "args": { + "External id": 1403547,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530401228.274, "dur": 54.998, + "args": { + "External id": 1403548,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530401320.916, "dur": 30.568, + "args": { + "External id": 1403549,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530401360.848, "dur": 43.214, + "args": { + "External id": 1403550,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530401411.708, "dur": 56.973, + "args": { + "External id": 1403551,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530401495.204, "dur": 25.779, + "args": { + "External id": 1403552,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530401529.652, "dur": 38.603, + "args": { + "External id": 1403553,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530401587.476, "dur": 19.391, + "args": { + "External id": 1403554,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12518 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.5)", "pid": 2338710, "tid": 2338710, + "ts": 6410530401754.789, "dur": 79.457, + "args": { + "External id": 1403555,"Record function id": 0, "Ev Idx": 12519 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530401910.251, "dur": 48.168, + "args": { + "External id": 1403556,"Record function id": 0, "Ev Idx": 12520 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 2338710, "tid": 2338710, + "ts": 6410530401967.880, "dur": 30443.425, + "args": { + "External id": 1403557,"Record function id": 0, "Ev Idx": 12521 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338710, "tid": 2338710, + "ts": 6410530401980.527, "dur": 986.042, + "args": { + "External id": 1403558,"Record function id": 0, "Ev Idx": 12522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530402100.116, "dur": 9.682, + "args": { + "External id": 1403559,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530402123.311, "dur": 41.214, + "args": { + "External id": 1403560,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402128.764, "dur": 2.511, + "args": { + "External id": 1403561,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402134.609, "dur": 0.506, + "args": { + "External id": 1403562,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402138.234, "dur": 0.642, + "args": { + "External id": 1403563,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402139.556, "dur": 0.601, + "args": { + "External id": 1403564,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402143.296, "dur": 0.776, + "args": { + "External id": 1403565,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402144.709, "dur": 0.472, + "args": { + "External id": 1403566,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402145.836, "dur": 4.140, + "args": { + "External id": 1403567,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402152.649, "dur": 0.699, + "args": { + "External id": 1403568,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402153.809, "dur": 0.706, + "args": { + "External id": 1403569,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530402176.431, "dur": 54.391, + "args": { + "External id": 1403570,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530402266.418, "dur": 130.879, + "args": { + "External id": 1403571,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530402279.630, "dur": 4.435, + "args": { + "External id": 1403572,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530402289.477, "dur": 10.384, + "args": { + "External id": 1403573,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530402294.357, "dur": 5.114, + "args": { + "External id": 1403574,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402297.723, "dur": 0.500, + "args": { + "External id": 1403575,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530402306.932, "dur": 33.832, + "args": { + "External id": 1403576,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402310.672, "dur": 2.079, + "args": { + "External id": 1403577,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402313.566, "dur": 0.507, + "args": { + "External id": 1403578,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402316.596, "dur": 0.497, + "args": { + "External id": 1403579,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402319.158, "dur": 2.409, + "args": { + "External id": 1403580,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402322.164, "dur": 0.546, + "args": { + "External id": 1403581,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402325.104, "dur": 0.567, + "args": { + "External id": 1403582,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402328.037, "dur": 0.389, + "args": { + "External id": 1403583,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402329.155, "dur": 0.480, + "args": { + "External id": 1403584,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530402331.521, "dur": 2.641, + "args": { + "External id": 1403585,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530402353.767, "dur": 35.183, + "args": { + "External id": 1403586,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530402470.370, "dur": 397.799, + "args": { + "External id": 1403587,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530402504.845, "dur": 358.488, + "args": { + "External id": 1403588,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12552, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530402514.877, "dur": 343.095, + "args": { + "External id": 1403589,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530402892.647, "dur": 2.331, + "args": { + "External id": 1403590,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12554, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338710, "tid": 2338710, + "ts": 6410530402987.916, "dur": 29224.755, + "args": { + "External id": 1403591,"Record function id": 0, "Ev Idx": 12555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403132.322, "dur": 7.096, + "args": { + "External id": 1403592,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403143.313, "dur": 1.272, + "args": { + "External id": 1403593,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403146.285, "dur": 3.358, + "args": { + "External id": 1403594,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403151.335, "dur": 1.242, + "args": { + "External id": 1403595,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403153.837, "dur": 1.473, + "args": { + "External id": 1403596,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403158.637, "dur": 1.575, + "args": { + "External id": 1403597,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403161.816, "dur": 1.559, + "args": { + "External id": 1403598,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403164.946, "dur": 2.272, + "args": { + "External id": 1403599,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403168.696, "dur": 0.864, + "args": { + "External id": 1403600,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530403173.220, "dur": 0.652, + "args": { + "External id": 1403601,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530403194.429, "dur": 28973.019, + "args": { + "External id": 1403602,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530403209.792, "dur": 28949.054, + "args": { + "External id": 1403603,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530403229.235, "dur": 16.319, + "args": { + "External id": 1403604,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530403248.750, "dur": 28874.065, + "args": { + "External id": 1403605,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530403251.406, "dur": 28870.699, + "args": { + "External id": 1403606,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530403258.536, "dur": 7.860, + "args": { + "External id": 1403607,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530403268.109, "dur": 28850.643, + "args": { + "External id": 1403608,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530432355.182, "dur": 28.877, + "args": { + "External id": 1403609,"Sequence number": 15108855, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12573 + } + }, + { + "ph": "s", "id": 211, "pid": 2338710, "tid": 2338710, "ts": 6410530432355.182, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530432370.908, "dur": 8.411, + "args": { + "External id": 1403610,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530432374.532, "dur": 4.595, + "args": { + "External id": 1403611,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530432463.535, "dur": 73.139, + "args": { + "External id": 1403612,"Record function id": 0, "Ev Idx": 12576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530432538.415, "dur": 1129.230, + "args": { + "External id": 1403613,"Record function id": 0, "Ev Idx": 12577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530432578.328, "dur": 1075.238, + "args": { + "External id": 1403614,"Sequence number": 15108856, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12578 + } + }, + { + "ph": "s", "id": 210, "pid": 2338710, "tid": 2338710, "ts": 6410530432578.328, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530432644.635, "dur": 51.884, + "args": { + "External id": 1403615,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530432708.816, "dur": 106.431, + "args": { + "External id": 1403616,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530432826.970, "dur": 38.822, + "args": { + "External id": 1403617,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530432874.530, "dur": 30.231, + "args": { + "External id": 1403618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530432930.288, "dur": 27.273, + "args": { + "External id": 1403619,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530432976.889, "dur": 17.530, + "args": { + "External id": 1403620,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530433015.237, "dur": 175.033, + "args": { + "External id": 1403621,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530433104.926, "dur": 14.690, + "args": { + "External id": 1403622,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530433112.547, "dur": 6.087, + "args": { + "External id": 1403623,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530433121.977, "dur": 3.587, + "args": { + "External id": 1403624,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530433126.725, "dur": 0.916, + "args": { + "External id": 1403625,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530433130.012, "dur": 5.671, + "args": { + "External id": 1403626,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530433201.807, "dur": 57.443, + "args": { + "External id": 1403627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530433294.324, "dur": 31.741, + "args": { + "External id": 1403628,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530433335.615, "dur": 43.946, + "args": { + "External id": 1403629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530433386.888, "dur": 50.637, + "args": { + "External id": 1403630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530433465.826, "dur": 27.708, + "args": { + "External id": 1403631,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530433501.579, "dur": 39.598, + "args": { + "External id": 1403632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530433561.864, "dur": 19.299, + "args": { + "External id": 1403633,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.6)", "pid": 2338710, "tid": 2338710, + "ts": 6410530433734.643, "dur": 80.654, + "args": { + "External id": 1403634,"Record function id": 0, "Ev Idx": 12598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530433888.322, "dur": 48.990, + "args": { + "External id": 1403635,"Record function id": 0, "Ev Idx": 12599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 2338710, "tid": 2338710, + "ts": 6410530433945.798, "dur": 31384.611, + "args": { + "External id": 1403636,"Record function id": 0, "Ev Idx": 12600 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338710, "tid": 2338710, + "ts": 6410530433957.772, "dur": 992.431, + "args": { + "External id": 1403637,"Record function id": 0, "Ev Idx": 12601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530434038.816, "dur": 8.415, + "args": { + "External id": 1403638,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530434103.853, "dur": 39.625, + "args": { + "External id": 1403639,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434108.981, "dur": 2.552, + "args": { + "External id": 1403640,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434117.344, "dur": 0.431, + "args": { + "External id": 1403641,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434118.777, "dur": 0.513, + "args": { + "External id": 1403642,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434120.184, "dur": 0.383, + "args": { + "External id": 1403643,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434125.279, "dur": 0.649, + "args": { + "External id": 1403644,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434126.727, "dur": 0.536, + "args": { + "External id": 1403645,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434129.942, "dur": 4.158, + "args": { + "External id": 1403646,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434134.986, "dur": 0.272, + "args": { + "External id": 1403647,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434135.928, "dur": 0.651, + "args": { + "External id": 1403648,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530434157.641, "dur": 59.728, + "args": { + "External id": 1403649,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530434252.943, "dur": 131.243, + "args": { + "External id": 1403650,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530434266.292, "dur": 5.060, + "args": { + "External id": 1403651,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530434276.514, "dur": 10.149, + "args": { + "External id": 1403652,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530434281.257, "dur": 5.025, + "args": { + "External id": 1403653,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434284.202, "dur": 0.804, + "args": { + "External id": 1403654,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530434295.083, "dur": 29.198, + "args": { + "External id": 1403655,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434296.484, "dur": 2.015, + "args": { + "External id": 1403656,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434299.473, "dur": 0.510, + "args": { + "External id": 1403657,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434301.666, "dur": 0.687, + "args": { + "External id": 1403658,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434305.464, "dur": 2.323, + "args": { + "External id": 1403659,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434309.650, "dur": 0.700, + "args": { + "External id": 1403660,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434310.819, "dur": 0.551, + "args": { + "External id": 1403661,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434313.968, "dur": 0.331, + "args": { + "External id": 1403662,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434316.709, "dur": 0.318, + "args": { + "External id": 1403663,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530434317.869, "dur": 2.310, + "args": { + "External id": 1403664,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530434340.766, "dur": 34.535, + "args": { + "External id": 1403665,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530434458.923, "dur": 393.877, + "args": { + "External id": 1403666,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530434492.464, "dur": 355.120, + "args": { + "External id": 1403667,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12631, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530434504.468, "dur": 337.809, + "args": { + "External id": 1403668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530434876.717, "dur": 2.391, + "args": { + "External id": 1403669,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12633, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338710, "tid": 2338710, + "ts": 6410530434970.792, "dur": 30120.474, + "args": { + "External id": 1403670,"Record function id": 0, "Ev Idx": 12634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435126.888, "dur": 7.771, + "args": { + "External id": 1403671,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435138.769, "dur": 1.199, + "args": { + "External id": 1403672,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435141.761, "dur": 2.975, + "args": { + "External id": 1403673,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435148.446, "dur": 0.821, + "args": { + "External id": 1403674,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435150.584, "dur": 1.106, + "args": { + "External id": 1403675,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435153.084, "dur": 1.126, + "args": { + "External id": 1403676,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435155.694, "dur": 0.999, + "args": { + "External id": 1403677,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435161.396, "dur": 2.232, + "args": { + "External id": 1403678,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435164.877, "dur": 0.651, + "args": { + "External id": 1403679,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530435166.747, "dur": 0.781, + "args": { + "External id": 1403680,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530435188.128, "dur": 29799.444, + "args": { + "External id": 1403681,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530435205.515, "dur": 29768.187, + "args": { + "External id": 1403682,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530435222.928, "dur": 16.098, + "args": { + "External id": 1403683,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530435242.659, "dur": 29678.509, + "args": { + "External id": 1403684,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530435245.321, "dur": 29674.665, + "args": { + "External id": 1403685,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530435251.435, "dur": 6.706, + "args": { + "External id": 1403686,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530435260.178, "dur": 29653.717, + "args": { + "External id": 1403687,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530465262.186, "dur": 38.794, + "args": { + "External id": 1403688,"Sequence number": 15108857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12652 + } + }, + { + "ph": "s", "id": 209, "pid": 2338710, "tid": 2338710, "ts": 6410530465262.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530465281.708, "dur": 14.274, + "args": { + "External id": 1403689,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530465288.442, "dur": 7.261, + "args": { + "External id": 1403690,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530465370.503, "dur": 84.381, + "args": { + "External id": 1403691,"Record function id": 0, "Ev Idx": 12655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530465457.901, "dur": 1350.660, + "args": { + "External id": 1403692,"Record function id": 0, "Ev Idx": 12656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530465501.878, "dur": 1291.163, + "args": { + "External id": 1403693,"Sequence number": 15108858, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12657 + } + }, + { + "ph": "s", "id": 208, "pid": 2338710, "tid": 2338710, "ts": 6410530465501.878, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530465579.878, "dur": 70.350, + "args": { + "External id": 1403694,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530465672.050, "dur": 122.825, + "args": { + "External id": 1403695,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530465821.588, "dur": 57.029, + "args": { + "External id": 1403696,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530465890.303, "dur": 33.211, + "args": { + "External id": 1403697,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530465969.528, "dur": 37.067, + "args": { + "External id": 1403698,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530466036.454, "dur": 61.202, + "args": { + "External id": 1403699,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530466135.949, "dur": 164.936, + "args": { + "External id": 1403700,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530466197.216, "dur": 13.390, + "args": { + "External id": 1403701,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530466203.214, "dur": 6.287, + "args": { + "External id": 1403702,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530466213.122, "dur": 3.723, + "args": { + "External id": 1403703,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530466229.119, "dur": 1.045, + "args": { + "External id": 1403704,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530466234.541, "dur": 7.173, + "args": { + "External id": 1403705,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530466313.704, "dur": 71.304, + "args": { + "External id": 1403706,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530466438.317, "dur": 36.254, + "args": { + "External id": 1403707,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530466489.212, "dur": 50.046, + "args": { + "External id": 1403708,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530466546.069, "dur": 36.829, + "args": { + "External id": 1403709,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530466605.859, "dur": 30.300, + "args": { + "External id": 1403710,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530466642.678, "dur": 36.798, + "args": { + "External id": 1403711,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530466699.780, "dur": 18.542, + "args": { + "External id": 1403712,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12676 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.7)", "pid": 2338710, "tid": 2338710, + "ts": 6410530466877.839, "dur": 82.024, + "args": { + "External id": 1403713,"Record function id": 0, "Ev Idx": 12677 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530467034.313, "dur": 113.411, + "args": { + "External id": 1403714,"Record function id": 0, "Ev Idx": 12678 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 2338710, "tid": 2338710, + "ts": 6410530467165.385, "dur": 30581.398, + "args": { + "External id": 1403715,"Record function id": 0, "Ev Idx": 12679 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338710, "tid": 2338710, + "ts": 6410530467180.333, "dur": 1146.149, + "args": { + "External id": 1403716,"Record function id": 0, "Ev Idx": 12680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530467289.430, "dur": 13.851, + "args": { + "External id": 1403717,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530467320.868, "dur": 47.997, + "args": { + "External id": 1403718,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467329.489, "dur": 2.695, + "args": { + "External id": 1403719,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467337.103, "dur": 0.631, + "args": { + "External id": 1403720,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467340.418, "dur": 0.594, + "args": { + "External id": 1403721,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467342.688, "dur": 0.582, + "args": { + "External id": 1403722,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467346.604, "dur": 0.624, + "args": { + "External id": 1403723,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467350.338, "dur": 0.499, + "args": { + "External id": 1403724,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467352.232, "dur": 4.169, + "args": { + "External id": 1403725,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467357.664, "dur": 0.384, + "args": { + "External id": 1403726,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467361.087, "dur": 0.336, + "args": { + "External id": 1403727,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530467383.225, "dur": 82.051, + "args": { + "External id": 1403728,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530467505.934, "dur": 138.360, + "args": { + "External id": 1403729,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530467521.717, "dur": 6.680, + "args": { + "External id": 1403730,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530467534.052, "dur": 13.806, + "args": { + "External id": 1403731,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530467541.239, "dur": 6.218, + "args": { + "External id": 1403732,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467544.664, "dur": 1.011, + "args": { + "External id": 1403733,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530467555.059, "dur": 32.925, + "args": { + "External id": 1403734,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467558.345, "dur": 2.147, + "args": { + "External id": 1403735,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467561.450, "dur": 0.539, + "args": { + "External id": 1403736,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467562.848, "dur": 0.574, + "args": { + "External id": 1403737,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467567.543, "dur": 2.955, + "args": { + "External id": 1403738,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467571.184, "dur": 0.534, + "args": { + "External id": 1403739,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467572.709, "dur": 0.316, + "args": { + "External id": 1403740,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467577.873, "dur": 0.469, + "args": { + "External id": 1403741,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467578.963, "dur": 0.621, + "args": { + "External id": 1403742,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530467581.804, "dur": 1.954, + "args": { + "External id": 1403743,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530467600.570, "dur": 34.531, + "args": { + "External id": 1403744,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530467704.828, "dur": 503.919, + "args": { + "External id": 1403745,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530467739.629, "dur": 462.516, + "args": { + "External id": 1403746,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12710, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530467752.464, "dur": 441.835, + "args": { + "External id": 1403747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530468237.511, "dur": 2.890, + "args": { + "External id": 1403748,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12712, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338710, "tid": 2338710, + "ts": 6410530468347.369, "dur": 29186.427, + "args": { + "External id": 1403749,"Record function id": 0, "Ev Idx": 12713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468477.246, "dur": 7.747, + "args": { + "External id": 1403750,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468489.006, "dur": 1.299, + "args": { + "External id": 1403751,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468491.850, "dur": 3.374, + "args": { + "External id": 1403752,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468497.114, "dur": 0.858, + "args": { + "External id": 1403753,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468499.183, "dur": 1.048, + "args": { + "External id": 1403754,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468501.551, "dur": 0.897, + "args": { + "External id": 1403755,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468506.493, "dur": 0.999, + "args": { + "External id": 1403756,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468508.641, "dur": 1.903, + "args": { + "External id": 1403757,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468511.746, "dur": 0.840, + "args": { + "External id": 1403758,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530468513.973, "dur": 0.758, + "args": { + "External id": 1403759,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530468546.366, "dur": 28931.370, + "args": { + "External id": 1403760,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530468565.464, "dur": 28901.478, + "args": { + "External id": 1403761,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530468581.521, "dur": 16.683, + "args": { + "External id": 1403762,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530468601.475, "dur": 28810.233, + "args": { + "External id": 1403763,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530468604.213, "dur": 28806.618, + "args": { + "External id": 1403764,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530468609.586, "dur": 5.585, + "args": { + "External id": 1403765,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530468617.021, "dur": 28790.389, + "args": { + "External id": 1403766,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530497685.543, "dur": 34.043, + "args": { + "External id": 1403767,"Sequence number": 15108859, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12731 + } + }, + { + "ph": "s", "id": 207, "pid": 2338710, "tid": 2338710, "ts": 6410530497685.543, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530497702.642, "dur": 12.224, + "args": { + "External id": 1403768,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530497708.773, "dur": 5.855, + "args": { + "External id": 1403769,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530497787.417, "dur": 71.174, + "args": { + "External id": 1403770,"Record function id": 0, "Ev Idx": 12734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530497860.003, "dur": 1122.662, + "args": { + "External id": 1403771,"Record function id": 0, "Ev Idx": 12735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530497901.044, "dur": 1067.558, + "args": { + "External id": 1403772,"Sequence number": 15108860, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12736 + } + }, + { + "ph": "s", "id": 206, "pid": 2338710, "tid": 2338710, "ts": 6410530497901.044, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530497967.116, "dur": 50.461, + "args": { + "External id": 1403773,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530498030.314, "dur": 138.897, + "args": { + "External id": 1403774,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530498192.186, "dur": 42.648, + "args": { + "External id": 1403775,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530498244.131, "dur": 29.813, + "args": { + "External id": 1403776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530498305.343, "dur": 29.908, + "args": { + "External id": 1403777,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530498355.082, "dur": 16.136, + "args": { + "External id": 1403778,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530498393.969, "dur": 152.277, + "args": { + "External id": 1403779,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530498462.558, "dur": 12.743, + "args": { + "External id": 1403780,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530498467.868, "dur": 6.511, + "args": { + "External id": 1403781,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530498479.289, "dur": 4.309, + "args": { + "External id": 1403782,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530498484.805, "dur": 0.781, + "args": { + "External id": 1403783,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530498488.004, "dur": 5.158, + "args": { + "External id": 1403784,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530498557.425, "dur": 53.810, + "args": { + "External id": 1403785,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530498644.485, "dur": 30.980, + "args": { + "External id": 1403786,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530498684.996, "dur": 43.883, + "args": { + "External id": 1403787,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530498736.253, "dur": 34.817, + "args": { + "External id": 1403788,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530498795.007, "dur": 24.575, + "args": { + "External id": 1403789,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530498827.832, "dur": 36.026, + "args": { + "External id": 1403790,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530498881.592, "dur": 18.240, + "args": { + "External id": 1403791,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12755 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.8)", "pid": 2338710, "tid": 2338710, + "ts": 6410530499048.297, "dur": 129.415, + "args": { + "External id": 1403792,"Record function id": 0, "Ev Idx": 12756 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530499260.121, "dur": 50.857, + "args": { + "External id": 1403793,"Record function id": 0, "Ev Idx": 12757 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 2338710, "tid": 2338710, + "ts": 6410530499320.073, "dur": 29929.912, + "args": { + "External id": 1403794,"Record function id": 0, "Ev Idx": 12758 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338710, "tid": 2338710, + "ts": 6410530499330.700, "dur": 1000.103, + "args": { + "External id": 1403795,"Record function id": 0, "Ev Idx": 12759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530499432.540, "dur": 11.604, + "args": { + "External id": 1403796,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530499461.049, "dur": 37.327, + "args": { + "External id": 1403797,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499466.403, "dur": 2.554, + "args": { + "External id": 1403798,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499472.769, "dur": 0.391, + "args": { + "External id": 1403799,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499475.572, "dur": 0.526, + "args": { + "External id": 1403800,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499476.954, "dur": 0.582, + "args": { + "External id": 1403801,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499479.573, "dur": 0.780, + "args": { + "External id": 1403802,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499482.844, "dur": 0.334, + "args": { + "External id": 1403803,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499483.834, "dur": 4.060, + "args": { + "External id": 1403804,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499489.932, "dur": 0.597, + "args": { + "External id": 1403805,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499491.196, "dur": 0.570, + "args": { + "External id": 1403806,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530499509.198, "dur": 60.749, + "args": { + "External id": 1403807,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530499607.069, "dur": 139.706, + "args": { + "External id": 1403808,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530499620.488, "dur": 4.452, + "args": { + "External id": 1403809,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530499630.084, "dur": 12.407, + "args": { + "External id": 1403810,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530499636.860, "dur": 5.204, + "args": { + "External id": 1403811,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499639.996, "dur": 0.765, + "args": { + "External id": 1403812,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530499648.829, "dur": 33.546, + "args": { + "External id": 1403813,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499651.807, "dur": 2.313, + "args": { + "External id": 1403814,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499659.112, "dur": 0.590, + "args": { + "External id": 1403815,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499660.304, "dur": 0.541, + "args": { + "External id": 1403816,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499665.099, "dur": 2.594, + "args": { + "External id": 1403817,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499668.313, "dur": 0.488, + "args": { + "External id": 1403818,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499670.796, "dur": 1.233, + "args": { + "External id": 1403819,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499672.761, "dur": 0.549, + "args": { + "External id": 1403820,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499673.849, "dur": 0.718, + "args": { + "External id": 1403821,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530499677.996, "dur": 0.398, + "args": { + "External id": 1403822,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530499703.071, "dur": 35.209, + "args": { + "External id": 1403823,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530499802.896, "dur": 414.938, + "args": { + "External id": 1403824,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530499835.739, "dur": 375.808, + "args": { + "External id": 1403825,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12789, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530499847.897, "dur": 356.426, + "args": { + "External id": 1403826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530500247.034, "dur": 2.854, + "args": { + "External id": 1403827,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12791, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338710, "tid": 2338710, + "ts": 6410530500353.155, "dur": 28656.315, + "args": { + "External id": 1403828,"Record function id": 0, "Ev Idx": 12792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500481.329, "dur": 7.251, + "args": { + "External id": 1403829,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500492.555, "dur": 1.284, + "args": { + "External id": 1403830,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500496.662, "dur": 3.799, + "args": { + "External id": 1403831,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500502.570, "dur": 0.904, + "args": { + "External id": 1403832,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500505.106, "dur": 1.146, + "args": { + "External id": 1403833,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500507.982, "dur": 0.936, + "args": { + "External id": 1403834,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500513.022, "dur": 1.500, + "args": { + "External id": 1403835,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500516.038, "dur": 2.042, + "args": { + "External id": 1403836,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500519.557, "dur": 1.011, + "args": { + "External id": 1403837,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530500521.819, "dur": 1.070, + "args": { + "External id": 1403838,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530500545.181, "dur": 28417.143, + "args": { + "External id": 1403839,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530500562.685, "dur": 28390.665, + "args": { + "External id": 1403840,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530500581.115, "dur": 18.011, + "args": { + "External id": 1403841,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530500602.876, "dur": 28315.068, + "args": { + "External id": 1403842,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530500605.330, "dur": 28311.982, + "args": { + "External id": 1403843,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530500611.222, "dur": 6.427, + "args": { + "External id": 1403844,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530500619.523, "dur": 28294.787, + "args": { + "External id": 1403845,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530529190.414, "dur": 31.875, + "args": { + "External id": 1403846,"Sequence number": 15108861, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12810 + } + }, + { + "ph": "s", "id": 205, "pid": 2338710, "tid": 2338710, "ts": 6410530529190.414, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530529207.303, "dur": 10.218, + "args": { + "External id": 1403847,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530529211.732, "dur": 5.464, + "args": { + "External id": 1403848,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530529290.377, "dur": 70.180, + "args": { + "External id": 1403849,"Record function id": 0, "Ev Idx": 12813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530529362.114, "dur": 1136.497, + "args": { + "External id": 1403850,"Record function id": 0, "Ev Idx": 12814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530529402.478, "dur": 1081.281, + "args": { + "External id": 1403851,"Sequence number": 15108862, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12815 + } + }, + { + "ph": "s", "id": 204, "pid": 2338710, "tid": 2338710, "ts": 6410530529402.478, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530529482.486, "dur": 51.378, + "args": { + "External id": 1403852,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530529546.825, "dur": 106.734, + "args": { + "External id": 1403853,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530529666.395, "dur": 41.631, + "args": { + "External id": 1403854,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530529717.602, "dur": 29.139, + "args": { + "External id": 1403855,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530529773.269, "dur": 27.202, + "args": { + "External id": 1403856,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530529820.129, "dur": 16.692, + "args": { + "External id": 1403857,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530529858.957, "dur": 131.287, + "args": { + "External id": 1403858,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530529909.126, "dur": 11.516, + "args": { + "External id": 1403859,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530529914.697, "dur": 5.080, + "args": { + "External id": 1403860,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530529923.580, "dur": 4.937, + "args": { + "External id": 1403861,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530529929.993, "dur": 1.446, + "args": { + "External id": 1403862,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530529933.773, "dur": 5.531, + "args": { + "External id": 1403863,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530530001.807, "dur": 46.651, + "args": { + "External id": 1403864,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530530126.197, "dur": 30.650, + "args": { + "External id": 1403865,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530530175.124, "dur": 47.318, + "args": { + "External id": 1403866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530530230.579, "dur": 35.004, + "args": { + "External id": 1403867,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530530291.818, "dur": 26.544, + "args": { + "External id": 1403868,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530530326.654, "dur": 36.406, + "args": { + "External id": 1403869,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530530380.302, "dur": 18.284, + "args": { + "External id": 1403870,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.9)", "pid": 2338710, "tid": 2338710, + "ts": 6410530530567.416, "dur": 82.424, + "args": { + "External id": 1403871,"Record function id": 0, "Ev Idx": 12835 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530530725.297, "dur": 49.057, + "args": { + "External id": 1403872,"Record function id": 0, "Ev Idx": 12836 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 2338710, "tid": 2338710, + "ts": 6410530530783.799, "dur": 32145.183, + "args": { + "External id": 1403873,"Record function id": 0, "Ev Idx": 12837 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338710, "tid": 2338710, + "ts": 6410530530791.662, "dur": 980.528, + "args": { + "External id": 1403874,"Record function id": 0, "Ev Idx": 12838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530530877.174, "dur": 9.392, + "args": { + "External id": 1403875,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530530899.348, "dur": 40.578, + "args": { + "External id": 1403876,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530905.153, "dur": 2.446, + "args": { + "External id": 1403877,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530912.381, "dur": 0.659, + "args": { + "External id": 1403878,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530914.484, "dur": 0.342, + "args": { + "External id": 1403879,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530916.895, "dur": 0.558, + "args": { + "External id": 1403880,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530920.221, "dur": 0.620, + "args": { + "External id": 1403881,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530922.287, "dur": 0.610, + "args": { + "External id": 1403882,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530924.380, "dur": 3.817, + "args": { + "External id": 1403883,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530930.111, "dur": 0.570, + "args": { + "External id": 1403884,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530530932.991, "dur": 0.608, + "args": { + "External id": 1403885,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530530951.138, "dur": 51.975, + "args": { + "External id": 1403886,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530531036.665, "dur": 174.179, + "args": { + "External id": 1403887,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530531049.110, "dur": 43.233, + "args": { + "External id": 1403888,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530531100.180, "dur": 14.132, + "args": { + "External id": 1403889,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530531107.355, "dur": 6.554, + "args": { + "External id": 1403890,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531111.342, "dur": 0.733, + "args": { + "External id": 1403891,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530531122.348, "dur": 32.510, + "args": { + "External id": 1403892,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531125.454, "dur": 2.892, + "args": { + "External id": 1403893,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531130.176, "dur": 0.527, + "args": { + "External id": 1403894,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531131.888, "dur": 0.330, + "args": { + "External id": 1403895,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531135.459, "dur": 2.410, + "args": { + "External id": 1403896,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531139.402, "dur": 0.402, + "args": { + "External id": 1403897,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531141.083, "dur": 0.419, + "args": { + "External id": 1403898,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531144.864, "dur": 0.371, + "args": { + "External id": 1403899,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531146.594, "dur": 0.439, + "args": { + "External id": 1403900,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530531148.335, "dur": 2.387, + "args": { + "External id": 1403901,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530531167.137, "dur": 35.173, + "args": { + "External id": 1403902,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530531266.395, "dur": 401.988, + "args": { + "External id": 1403903,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530531299.655, "dur": 363.314, + "args": { + "External id": 1403904,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12868, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530531329.532, "dur": 326.875, + "args": { + "External id": 1403905,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530531695.384, "dur": 2.512, + "args": { + "External id": 1403906,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12870, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338710, "tid": 2338710, + "ts": 6410530531792.718, "dur": 30921.156, + "args": { + "External id": 1403907,"Record function id": 0, "Ev Idx": 12871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531897.866, "dur": 6.426, + "args": { + "External id": 1403908,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531909.170, "dur": 1.031, + "args": { + "External id": 1403909,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531912.297, "dur": 3.373, + "args": { + "External id": 1403910,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531917.725, "dur": 0.770, + "args": { + "External id": 1403911,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531919.982, "dur": 0.760, + "args": { + "External id": 1403912,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531922.105, "dur": 0.804, + "args": { + "External id": 1403913,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531926.835, "dur": 0.885, + "args": { + "External id": 1403914,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531929.123, "dur": 2.192, + "args": { + "External id": 1403915,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531932.902, "dur": 0.735, + "args": { + "External id": 1403916,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530531935.614, "dur": 0.828, + "args": { + "External id": 1403917,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530531955.775, "dur": 30702.233, + "args": { + "External id": 1403918,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530531971.037, "dur": 30676.715, + "args": { + "External id": 1403919,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530531986.017, "dur": 15.945, + "args": { + "External id": 1403920,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530532005.595, "dur": 30600.853, + "args": { + "External id": 1403921,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530532008.230, "dur": 30597.399, + "args": { + "External id": 1403922,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530532014.217, "dur": 6.513, + "args": { + "External id": 1403923,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530532022.470, "dur": 30579.161, + "args": { + "External id": 1403924,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530562869.806, "dur": 31.700, + "args": { + "External id": 1403925,"Sequence number": 15108863, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12889 + } + }, + { + "ph": "s", "id": 203, "pid": 2338710, "tid": 2338710, "ts": 6410530562869.806, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530562886.411, "dur": 10.341, + "args": { + "External id": 1403926,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530562890.967, "dur": 5.584, + "args": { + "External id": 1403927,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530562968.797, "dur": 68.671, + "args": { + "External id": 1403928,"Record function id": 0, "Ev Idx": 12892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530563039.134, "dur": 1167.064, + "args": { + "External id": 1403929,"Record function id": 0, "Ev Idx": 12893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530563125.031, "dur": 1067.509, + "args": { + "External id": 1403930,"Sequence number": 15108864, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12894 + } + }, + { + "ph": "s", "id": 202, "pid": 2338710, "tid": 2338710, "ts": 6410530563125.031, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530563193.416, "dur": 51.860, + "args": { + "External id": 1403931,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530563258.898, "dur": 105.173, + "args": { + "External id": 1403932,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530563376.251, "dur": 56.382, + "args": { + "External id": 1403933,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530563444.120, "dur": 33.768, + "args": { + "External id": 1403934,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530563506.761, "dur": 25.786, + "args": { + "External id": 1403935,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530563551.958, "dur": 17.051, + "args": { + "External id": 1403936,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530563592.712, "dur": 132.447, + "args": { + "External id": 1403937,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530563644.241, "dur": 11.602, + "args": { + "External id": 1403938,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530563649.892, "dur": 5.189, + "args": { + "External id": 1403939,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530563658.413, "dur": 5.159, + "args": { + "External id": 1403940,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530563664.887, "dur": 0.874, + "args": { + "External id": 1403941,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530563668.192, "dur": 4.458, + "args": { + "External id": 1403942,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530563735.614, "dur": 48.185, + "args": { + "External id": 1403943,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530563816.408, "dur": 28.550, + "args": { + "External id": 1403944,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530563855.208, "dur": 42.333, + "args": { + "External id": 1403945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530563905.819, "dur": 35.079, + "args": { + "External id": 1403946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530563964.052, "dur": 27.365, + "args": { + "External id": 1403947,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530563998.814, "dur": 36.189, + "args": { + "External id": 1403948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530564052.079, "dur": 66.950, + "args": { + "External id": 1403949,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12913 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.10)", "pid": 2338710, "tid": 2338710, + "ts": 6410530564273.077, "dur": 82.497, + "args": { + "External id": 1403950,"Record function id": 0, "Ev Idx": 12914 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530564446.519, "dur": 48.064, + "args": { + "External id": 1403951,"Record function id": 0, "Ev Idx": 12915 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 2338710, "tid": 2338710, + "ts": 6410530564503.919, "dur": 30478.263, + "args": { + "External id": 1403952,"Record function id": 0, "Ev Idx": 12916 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338710, "tid": 2338710, + "ts": 6410530564510.688, "dur": 947.444, + "args": { + "External id": 1403953,"Record function id": 0, "Ev Idx": 12917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530564593.506, "dur": 10.071, + "args": { + "External id": 1403954,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530564616.436, "dur": 38.510, + "args": { + "External id": 1403955,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564622.350, "dur": 2.284, + "args": { + "External id": 1403956,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564628.832, "dur": 0.620, + "args": { + "External id": 1403957,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564631.110, "dur": 0.491, + "args": { + "External id": 1403958,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564633.346, "dur": 0.544, + "args": { + "External id": 1403959,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564636.703, "dur": 0.442, + "args": { + "External id": 1403960,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564638.561, "dur": 0.360, + "args": { + "External id": 1403961,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564641.152, "dur": 3.861, + "args": { + "External id": 1403962,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564646.540, "dur": 0.522, + "args": { + "External id": 1403963,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564648.540, "dur": 0.479, + "args": { + "External id": 1403964,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530564669.248, "dur": 56.809, + "args": { + "External id": 1403965,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530564759.950, "dur": 125.864, + "args": { + "External id": 1403966,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530564772.570, "dur": 4.360, + "args": { + "External id": 1403967,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530564782.273, "dur": 13.230, + "args": { + "External id": 1403968,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530564789.513, "dur": 5.580, + "args": { + "External id": 1403969,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564793.210, "dur": 0.558, + "args": { + "External id": 1403970,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530564802.540, "dur": 29.461, + "args": { + "External id": 1403971,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564804.903, "dur": 0.414, + "args": { + "External id": 1403972,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564807.248, "dur": 2.246, + "args": { + "External id": 1403973,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564811.172, "dur": 0.409, + "args": { + "External id": 1403974,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564813.458, "dur": 2.379, + "args": { + "External id": 1403975,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564818.986, "dur": 0.295, + "args": { + "External id": 1403976,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564820.781, "dur": 0.449, + "args": { + "External id": 1403977,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564823.068, "dur": 0.336, + "args": { + "External id": 1403978,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564826.374, "dur": 0.415, + "args": { + "External id": 1403979,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530564828.077, "dur": 0.396, + "args": { + "External id": 1403980,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530564844.877, "dur": 33.157, + "args": { + "External id": 1403981,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530564939.461, "dur": 399.365, + "args": { + "External id": 1403982,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530564972.715, "dur": 360.607, + "args": { + "External id": 1403983,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12947, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530564982.591, "dur": 344.788, + "args": { + "External id": 1403984,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530565364.521, "dur": 2.620, + "args": { + "External id": 1403985,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 12949, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338710, "tid": 2338710, + "ts": 6410530565480.614, "dur": 29304.048, + "args": { + "External id": 1403986,"Record function id": 0, "Ev Idx": 12950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565588.141, "dur": 7.242, + "args": { + "External id": 1403987,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565599.672, "dur": 0.934, + "args": { + "External id": 1403988,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565602.502, "dur": 2.853, + "args": { + "External id": 1403989,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565607.052, "dur": 1.047, + "args": { + "External id": 1403990,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565609.597, "dur": 0.945, + "args": { + "External id": 1403991,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565612.227, "dur": 0.836, + "args": { + "External id": 1403992,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565616.797, "dur": 0.662, + "args": { + "External id": 1403993,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565619.207, "dur": 1.845, + "args": { + "External id": 1403994,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565622.294, "dur": 0.616, + "args": { + "External id": 1403995,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530565624.461, "dur": 0.810, + "args": { + "External id": 1403996,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530565645.336, "dur": 29096.765, + "args": { + "External id": 1403997,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530565661.163, "dur": 29072.655, + "args": { + "External id": 1403998,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530565680.269, "dur": 16.353, + "args": { + "External id": 1403999,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530565700.022, "dur": 28999.916, + "args": { + "External id": 1404000,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530565702.499, "dur": 28996.924, + "args": { + "External id": 1404001,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530565708.702, "dur": 6.431, + "args": { + "External id": 1404002,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530565716.903, "dur": 28979.322, + "args": { + "External id": 1404003,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530594927.462, "dur": 30.287, + "args": { + "External id": 1404004,"Sequence number": 15108865, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12968 + } + }, + { + "ph": "s", "id": 201, "pid": 2338710, "tid": 2338710, "ts": 6410530594927.462, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530594944.600, "dur": 8.564, + "args": { + "External id": 1404005,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530594948.496, "dur": 4.477, + "args": { + "External id": 1404006,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530595020.712, "dur": 104.860, + "args": { + "External id": 1404007,"Record function id": 0, "Ev Idx": 12971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530595128.535, "dur": 1127.393, + "args": { + "External id": 1404008,"Record function id": 0, "Ev Idx": 12972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530595172.359, "dur": 1069.893, + "args": { + "External id": 1404009,"Sequence number": 15108866, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12973 + } + }, + { + "ph": "s", "id": 200, "pid": 2338710, "tid": 2338710, "ts": 6410530595172.359, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530595243.211, "dur": 48.254, + "args": { + "External id": 1404010,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530595303.824, "dur": 105.464, + "args": { + "External id": 1404011,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530595439.298, "dur": 43.738, + "args": { + "External id": 1404012,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530595492.319, "dur": 30.028, + "args": { + "External id": 1404013,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530595551.691, "dur": 25.795, + "args": { + "External id": 1404014,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530595596.923, "dur": 18.141, + "args": { + "External id": 1404015,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530595636.659, "dur": 129.710, + "args": { + "External id": 1404016,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530595688.299, "dur": 11.480, + "args": { + "External id": 1404017,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530595693.582, "dur": 5.323, + "args": { + "External id": 1404018,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530595702.369, "dur": 3.896, + "args": { + "External id": 1404019,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530595707.433, "dur": 1.105, + "args": { + "External id": 1404020,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530595710.832, "dur": 5.432, + "args": { + "External id": 1404021,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530595776.540, "dur": 47.988, + "args": { + "External id": 1404022,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530595856.831, "dur": 29.184, + "args": { + "External id": 1404023,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530595895.714, "dur": 43.217, + "args": { + "External id": 1404024,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530595947.341, "dur": 34.634, + "args": { + "External id": 1404025,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530596003.074, "dur": 26.405, + "args": { + "External id": 1404026,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530596037.701, "dur": 86.006, + "args": { + "External id": 1404027,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530596149.553, "dur": 20.352, + "args": { + "External id": 1404028,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12992 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.11)", "pid": 2338710, "tid": 2338710, + "ts": 6410530596322.354, "dur": 80.880, + "args": { + "External id": 1404029,"Record function id": 0, "Ev Idx": 12993 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530596496.005, "dur": 50.006, + "args": { + "External id": 1404030,"Record function id": 0, "Ev Idx": 12994 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 2338710, "tid": 2338710, + "ts": 6410530596555.602, "dur": 31400.736, + "args": { + "External id": 1404031,"Record function id": 0, "Ev Idx": 12995 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338710, "tid": 2338710, + "ts": 6410530596564.544, "dur": 940.770, + "args": { + "External id": 1404032,"Record function id": 0, "Ev Idx": 12996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530596647.461, "dur": 10.320, + "args": { + "External id": 1404033,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530596673.239, "dur": 36.722, + "args": { + "External id": 1404034,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596678.872, "dur": 2.394, + "args": { + "External id": 1404035,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596685.758, "dur": 0.468, + "args": { + "External id": 1404036,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596687.230, "dur": 0.448, + "args": { + "External id": 1404037,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596689.131, "dur": 2.097, + "args": { + "External id": 1404038,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596692.664, "dur": 0.336, + "args": { + "External id": 1404039,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596694.413, "dur": 0.494, + "args": { + "External id": 1404040,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596698.021, "dur": 2.621, + "args": { + "External id": 1404041,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596701.427, "dur": 0.337, + "args": { + "External id": 1404042,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596703.529, "dur": 0.363, + "args": { + "External id": 1404043,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530596721.136, "dur": 56.787, + "args": { + "External id": 1404044,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530596811.033, "dur": 120.114, + "args": { + "External id": 1404045,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530596824.070, "dur": 3.857, + "args": { + "External id": 1404046,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530596833.129, "dur": 14.641, + "args": { + "External id": 1404047,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530596840.158, "dur": 7.201, + "args": { + "External id": 1404048,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596843.590, "dur": 2.386, + "args": { + "External id": 1404049,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530596854.511, "dur": 26.807, + "args": { + "External id": 1404050,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596856.289, "dur": 0.587, + "args": { + "External id": 1404051,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596858.340, "dur": 0.444, + "args": { + "External id": 1404052,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596860.088, "dur": 0.346, + "args": { + "External id": 1404053,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596863.841, "dur": 2.327, + "args": { + "External id": 1404054,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596867.689, "dur": 0.378, + "args": { + "External id": 1404055,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596869.270, "dur": 2.200, + "args": { + "External id": 1404056,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596872.567, "dur": 0.271, + "args": { + "External id": 1404057,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596873.674, "dur": 0.395, + "args": { + "External id": 1404058,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530596877.167, "dur": 0.417, + "args": { + "External id": 1404059,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530596892.389, "dur": 30.836, + "args": { + "External id": 1404060,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530596982.693, "dur": 400.940, + "args": { + "External id": 1404061,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530597014.225, "dur": 363.377, + "args": { + "External id": 1404062,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13026, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530597024.015, "dur": 345.110, + "args": { + "External id": 1404063,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530597409.596, "dur": 2.530, + "args": { + "External id": 1404064,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13028, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338710, "tid": 2338710, + "ts": 6410530597526.931, "dur": 30230.360, + "args": { + "External id": 1404065,"Record function id": 0, "Ev Idx": 13029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597629.810, "dur": 6.680, + "args": { + "External id": 1404066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597641.191, "dur": 0.868, + "args": { + "External id": 1404067,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597643.997, "dur": 3.128, + "args": { + "External id": 1404068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597649.020, "dur": 0.645, + "args": { + "External id": 1404069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597651.132, "dur": 1.113, + "args": { + "External id": 1404070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597654.096, "dur": 0.674, + "args": { + "External id": 1404071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597658.505, "dur": 0.843, + "args": { + "External id": 1404072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597660.705, "dur": 1.924, + "args": { + "External id": 1404073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597663.776, "dur": 0.866, + "args": { + "External id": 1404074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530597666.474, "dur": 0.912, + "args": { + "External id": 1404075,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530597686.352, "dur": 30019.847, + "args": { + "External id": 1404076,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530597701.214, "dur": 29995.629, + "args": { + "External id": 1404077,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530597720.199, "dur": 16.846, + "args": { + "External id": 1404078,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530597740.651, "dur": 29918.826, + "args": { + "External id": 1404079,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530597743.085, "dur": 29915.577, + "args": { + "External id": 1404080,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530597749.447, "dur": 6.310, + "args": { + "External id": 1404081,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530597757.761, "dur": 29897.056, + "args": { + "External id": 1404082,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530627900.549, "dur": 31.481, + "args": { + "External id": 1404083,"Sequence number": 15108867, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13047 + } + }, + { + "ph": "s", "id": 199, "pid": 2338710, "tid": 2338710, "ts": 6410530627900.549, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530627916.859, "dur": 10.480, + "args": { + "External id": 1404084,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530627921.522, "dur": 5.602, + "args": { + "External id": 1404085,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530627994.929, "dur": 99.513, + "args": { + "External id": 1404086,"Record function id": 0, "Ev Idx": 13050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530628097.325, "dur": 1123.400, + "args": { + "External id": 1404087,"Record function id": 0, "Ev Idx": 13051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530628140.740, "dur": 1065.965, + "args": { + "External id": 1404088,"Sequence number": 15108868, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13052 + } + }, + { + "ph": "s", "id": 198, "pid": 2338710, "tid": 2338710, "ts": 6410530628140.740, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530628209.095, "dur": 53.300, + "args": { + "External id": 1404089,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530628275.038, "dur": 106.941, + "args": { + "External id": 1404090,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530628394.792, "dur": 53.950, + "args": { + "External id": 1404091,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530628458.875, "dur": 33.178, + "args": { + "External id": 1404092,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530628519.190, "dur": 25.709, + "args": { + "External id": 1404093,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530628563.636, "dur": 16.642, + "args": { + "External id": 1404094,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530628602.127, "dur": 128.666, + "args": { + "External id": 1404095,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530628652.142, "dur": 11.736, + "args": { + "External id": 1404096,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530628657.871, "dur": 5.015, + "args": { + "External id": 1404097,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530628666.608, "dur": 4.684, + "args": { + "External id": 1404098,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530628672.983, "dur": 1.034, + "args": { + "External id": 1404099,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530628676.395, "dur": 4.251, + "args": { + "External id": 1404100,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530628741.543, "dur": 48.896, + "args": { + "External id": 1404101,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530628822.434, "dur": 28.991, + "args": { + "External id": 1404102,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530628860.335, "dur": 42.305, + "args": { + "External id": 1404103,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530628910.997, "dur": 35.040, + "args": { + "External id": 1404104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530628976.361, "dur": 27.470, + "args": { + "External id": 1404105,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530629011.668, "dur": 36.038, + "args": { + "External id": 1404106,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530629116.282, "dur": 21.507, + "args": { + "External id": 1404107,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13071 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.12)", "pid": 2338710, "tid": 2338710, + "ts": 6410530629286.065, "dur": 79.949, + "args": { + "External id": 1404108,"Record function id": 0, "Ev Idx": 13072 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530629457.702, "dur": 49.343, + "args": { + "External id": 1404109,"Record function id": 0, "Ev Idx": 13073 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 2338710, "tid": 2338710, + "ts": 6410530629516.751, "dur": 32740.528, + "args": { + "External id": 1404110,"Record function id": 0, "Ev Idx": 13074 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338710, "tid": 2338710, + "ts": 6410530629524.230, "dur": 816.624, + "args": { + "External id": 1404111,"Record function id": 0, "Ev Idx": 13075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530629606.208, "dur": 10.360, + "args": { + "External id": 1404112,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530629630.293, "dur": 37.407, + "args": { + "External id": 1404113,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629636.034, "dur": 2.373, + "args": { + "External id": 1404114,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629642.403, "dur": 0.779, + "args": { + "External id": 1404115,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629644.977, "dur": 0.814, + "args": { + "External id": 1404116,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629647.213, "dur": 0.627, + "args": { + "External id": 1404117,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629651.145, "dur": 0.669, + "args": { + "External id": 1404118,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629652.965, "dur": 0.488, + "args": { + "External id": 1404119,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629654.561, "dur": 4.151, + "args": { + "External id": 1404120,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629659.832, "dur": 0.497, + "args": { + "External id": 1404121,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629661.428, "dur": 0.564, + "args": { + "External id": 1404122,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530629678.111, "dur": 53.176, + "args": { + "External id": 1404123,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530629767.735, "dur": 120.665, + "args": { + "External id": 1404124,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530629780.334, "dur": 4.449, + "args": { + "External id": 1404125,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530629790.134, "dur": 10.285, + "args": { + "External id": 1404126,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530629794.649, "dur": 5.378, + "args": { + "External id": 1404127,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629798.470, "dur": 0.400, + "args": { + "External id": 1404128,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530629806.782, "dur": 27.676, + "args": { + "External id": 1404129,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629808.540, "dur": 1.815, + "args": { + "External id": 1404130,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629811.725, "dur": 0.533, + "args": { + "External id": 1404131,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629813.702, "dur": 0.339, + "args": { + "External id": 1404132,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629817.323, "dur": 2.441, + "args": { + "External id": 1404133,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629820.935, "dur": 0.450, + "args": { + "External id": 1404134,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629822.649, "dur": 0.233, + "args": { + "External id": 1404135,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629825.745, "dur": 0.324, + "args": { + "External id": 1404136,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629827.204, "dur": 0.305, + "args": { + "External id": 1404137,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530629828.838, "dur": 1.890, + "args": { + "External id": 1404138,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530629848.311, "dur": 32.371, + "args": { + "External id": 1404139,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530629940.683, "dur": 303.555, + "args": { + "External id": 1404140,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530629973.389, "dur": 265.148, + "args": { + "External id": 1404141,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13105, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530629983.322, "dur": 249.780, + "args": { + "External id": 1404142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530630269.594, "dur": 2.322, + "args": { + "External id": 1404143,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13107, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338710, "tid": 2338710, + "ts": 6410530630360.796, "dur": 31654.286, + "args": { + "External id": 1404144,"Record function id": 0, "Ev Idx": 13108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630477.290, "dur": 6.435, + "args": { + "External id": 1404145,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630487.957, "dur": 1.148, + "args": { + "External id": 1404146,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630490.987, "dur": 2.675, + "args": { + "External id": 1404147,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630495.320, "dur": 0.900, + "args": { + "External id": 1404148,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630497.580, "dur": 1.098, + "args": { + "External id": 1404149,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630500.069, "dur": 1.177, + "args": { + "External id": 1404150,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630504.996, "dur": 0.813, + "args": { + "External id": 1404151,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630507.247, "dur": 1.994, + "args": { + "External id": 1404152,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630511.049, "dur": 0.757, + "args": { + "External id": 1404153,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530630513.107, "dur": 0.689, + "args": { + "External id": 1404154,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530630533.567, "dur": 31428.046, + "args": { + "External id": 1404155,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530630549.120, "dur": 31403.067, + "args": { + "External id": 1404156,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530630566.465, "dur": 15.537, + "args": { + "External id": 1404157,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530630585.549, "dur": 31328.068, + "args": { + "External id": 1404158,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530630588.291, "dur": 31324.509, + "args": { + "External id": 1404159,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530630593.889, "dur": 4.763, + "args": { + "External id": 1404160,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530630600.401, "dur": 31308.569, + "args": { + "External id": 1404161,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530662196.288, "dur": 33.403, + "args": { + "External id": 1404162,"Sequence number": 15108869, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13126 + } + }, + { + "ph": "s", "id": 197, "pid": 2338710, "tid": 2338710, "ts": 6410530662196.288, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530662213.645, "dur": 10.806, + "args": { + "External id": 1404163,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530662218.282, "dur": 5.837, + "args": { + "External id": 1404164,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530662296.139, "dur": 69.165, + "args": { + "External id": 1404165,"Record function id": 0, "Ev Idx": 13129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530662366.682, "dur": 1142.780, + "args": { + "External id": 1404166,"Record function id": 0, "Ev Idx": 13130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530662406.772, "dur": 1087.495, + "args": { + "External id": 1404167,"Sequence number": 15108870, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13131 + } + }, + { + "ph": "s", "id": 196, "pid": 2338710, "tid": 2338710, "ts": 6410530662406.772, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530662487.132, "dur": 50.416, + "args": { + "External id": 1404168,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530662550.588, "dur": 104.031, + "args": { + "External id": 1404169,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530662666.275, "dur": 39.050, + "args": { + "External id": 1404170,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530662715.192, "dur": 30.787, + "args": { + "External id": 1404171,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530662773.822, "dur": 27.886, + "args": { + "External id": 1404172,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530662821.028, "dur": 18.945, + "args": { + "External id": 1404173,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530662862.055, "dur": 131.416, + "args": { + "External id": 1404174,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530662913.023, "dur": 10.945, + "args": { + "External id": 1404175,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530662918.325, "dur": 4.674, + "args": { + "External id": 1404176,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530662926.647, "dur": 4.872, + "args": { + "External id": 1404177,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530662932.719, "dur": 1.007, + "args": { + "External id": 1404178,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530662936.139, "dur": 5.430, + "args": { + "External id": 1404179,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530663004.177, "dur": 95.661, + "args": { + "External id": 1404180,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530663138.535, "dur": 32.991, + "args": { + "External id": 1404181,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530663182.018, "dur": 48.424, + "args": { + "External id": 1404182,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530663238.853, "dur": 35.731, + "args": { + "External id": 1404183,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530663298.106, "dur": 25.852, + "args": { + "External id": 1404184,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530663333.040, "dur": 38.026, + "args": { + "External id": 1404185,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530663388.691, "dur": 18.146, + "args": { + "External id": 1404186,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13150 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.13)", "pid": 2338710, "tid": 2338710, + "ts": 6410530663577.045, "dur": 78.049, + "args": { + "External id": 1404187,"Record function id": 0, "Ev Idx": 13151 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530663728.941, "dur": 49.610, + "args": { + "External id": 1404188,"Record function id": 0, "Ev Idx": 13152 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 2338710, "tid": 2338710, + "ts": 6410530663787.512, "dur": 30663.736, + "args": { + "External id": 1404189,"Record function id": 0, "Ev Idx": 13153 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338710, "tid": 2338710, + "ts": 6410530663795.667, "dur": 1018.484, + "args": { + "External id": 1404190,"Record function id": 0, "Ev Idx": 13154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530663879.982, "dur": 8.799, + "args": { + "External id": 1404191,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530663901.713, "dur": 46.389, + "args": { + "External id": 1404192,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663912.188, "dur": 2.393, + "args": { + "External id": 1404193,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663920.235, "dur": 0.613, + "args": { + "External id": 1404194,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663922.232, "dur": 0.532, + "args": { + "External id": 1404195,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663923.920, "dur": 1.801, + "args": { + "External id": 1404196,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663926.827, "dur": 0.647, + "args": { + "External id": 1404197,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663930.508, "dur": 0.493, + "args": { + "External id": 1404198,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663934.255, "dur": 2.856, + "args": { + "External id": 1404199,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663937.904, "dur": 0.500, + "args": { + "External id": 1404200,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530663939.543, "dur": 2.585, + "args": { + "External id": 1404201,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530663960.297, "dur": 55.384, + "args": { + "External id": 1404202,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530664049.042, "dur": 183.746, + "args": { + "External id": 1404203,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530664113.578, "dur": 6.438, + "args": { + "External id": 1404204,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530664128.687, "dur": 10.880, + "args": { + "External id": 1404205,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530664133.109, "dur": 6.068, + "args": { + "External id": 1404206,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664136.838, "dur": 0.669, + "args": { + "External id": 1404207,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530664147.389, "dur": 26.127, + "args": { + "External id": 1404208,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664149.596, "dur": 0.468, + "args": { + "External id": 1404209,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664151.345, "dur": 0.753, + "args": { + "External id": 1404210,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664153.401, "dur": 2.576, + "args": { + "External id": 1404211,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664156.829, "dur": 2.713, + "args": { + "External id": 1404212,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664160.627, "dur": 0.299, + "args": { + "External id": 1404213,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664163.535, "dur": 0.508, + "args": { + "External id": 1404214,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664165.084, "dur": 0.238, + "args": { + "External id": 1404215,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664166.185, "dur": 0.329, + "args": { + "External id": 1404216,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530664169.147, "dur": 0.306, + "args": { + "External id": 1404217,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530664186.617, "dur": 37.712, + "args": { + "External id": 1404218,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530664290.330, "dur": 418.548, + "args": { + "External id": 1404219,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530664323.430, "dur": 379.841, + "args": { + "External id": 1404220,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13184, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530664333.532, "dur": 362.975, + "args": { + "External id": 1404221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530664735.436, "dur": 2.786, + "args": { + "External id": 1404222,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13186, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338710, "tid": 2338710, + "ts": 6410530664835.144, "dur": 29393.263, + "args": { + "External id": 1404223,"Record function id": 0, "Ev Idx": 13187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664942.796, "dur": 6.235, + "args": { + "External id": 1404224,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664953.079, "dur": 1.018, + "args": { + "External id": 1404225,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664956.035, "dur": 3.292, + "args": { + "External id": 1404226,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664961.053, "dur": 0.658, + "args": { + "External id": 1404227,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664963.138, "dur": 0.962, + "args": { + "External id": 1404228,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664965.318, "dur": 0.999, + "args": { + "External id": 1404229,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664970.127, "dur": 0.991, + "args": { + "External id": 1404230,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664972.318, "dur": 2.029, + "args": { + "External id": 1404231,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664975.782, "dur": 0.901, + "args": { + "External id": 1404232,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530664978.045, "dur": 0.793, + "args": { + "External id": 1404233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530664998.992, "dur": 29176.043, + "args": { + "External id": 1404234,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530665015.057, "dur": 29150.360, + "args": { + "External id": 1404235,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530665032.843, "dur": 17.253, + "args": { + "External id": 1404236,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530665103.368, "dur": 29024.651, + "args": { + "External id": 1404237,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530665106.183, "dur": 29021.143, + "args": { + "External id": 1404238,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530665112.453, "dur": 6.153, + "args": { + "External id": 1404239,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530665120.720, "dur": 29003.266, + "args": { + "External id": 1404240,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530694378.694, "dur": 32.691, + "args": { + "External id": 1404241,"Sequence number": 15108871, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13205 + } + }, + { + "ph": "s", "id": 195, "pid": 2338710, "tid": 2338710, "ts": 6410530694378.694, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530694396.470, "dur": 10.053, + "args": { + "External id": 1404242,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530694400.739, "dur": 5.602, + "args": { + "External id": 1404243,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530694493.030, "dur": 72.509, + "args": { + "External id": 1404244,"Record function id": 0, "Ev Idx": 13208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530694566.780, "dur": 1137.658, + "args": { + "External id": 1404245,"Record function id": 0, "Ev Idx": 13209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530694608.875, "dur": 1082.105, + "args": { + "External id": 1404246,"Sequence number": 15108872, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13210 + } + }, + { + "ph": "s", "id": 194, "pid": 2338710, "tid": 2338710, "ts": 6410530694608.875, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530694676.083, "dur": 50.509, + "args": { + "External id": 1404247,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530694739.341, "dur": 104.704, + "args": { + "External id": 1404248,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530694856.919, "dur": 37.563, + "args": { + "External id": 1404249,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530694904.183, "dur": 29.959, + "args": { + "External id": 1404250,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530694959.288, "dur": 27.788, + "args": { + "External id": 1404251,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530695007.482, "dur": 16.606, + "args": { + "External id": 1404252,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530695045.317, "dur": 196.815, + "args": { + "External id": 1404253,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530695155.982, "dur": 12.762, + "args": { + "External id": 1404254,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530695161.342, "dur": 6.096, + "args": { + "External id": 1404255,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530695171.306, "dur": 3.451, + "args": { + "External id": 1404256,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530695175.916, "dur": 1.134, + "args": { + "External id": 1404257,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530695180.815, "dur": 5.506, + "args": { + "External id": 1404258,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530695253.394, "dur": 55.353, + "args": { + "External id": 1404259,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530695340.906, "dur": 30.517, + "args": { + "External id": 1404260,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530695382.462, "dur": 56.404, + "args": { + "External id": 1404261,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530695448.370, "dur": 38.033, + "args": { + "External id": 1404262,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530695509.015, "dur": 29.101, + "args": { + "External id": 1404263,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530695543.821, "dur": 37.095, + "args": { + "External id": 1404264,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530695601.454, "dur": 20.409, + "args": { + "External id": 1404265,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.14)", "pid": 2338710, "tid": 2338710, + "ts": 6410530695770.584, "dur": 80.408, + "args": { + "External id": 1404266,"Record function id": 0, "Ev Idx": 13230 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530695927.470, "dur": 45.732, + "args": { + "External id": 1404267,"Record function id": 0, "Ev Idx": 13231 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 2338710, "tid": 2338710, + "ts": 6410530695982.037, "dur": 30996.302, + "args": { + "External id": 1404268,"Record function id": 0, "Ev Idx": 13232 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338710, "tid": 2338710, + "ts": 6410530695990.224, "dur": 966.562, + "args": { + "External id": 1404269,"Record function id": 0, "Ev Idx": 13233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530696128.062, "dur": 10.936, + "args": { + "External id": 1404270,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530696153.282, "dur": 39.476, + "args": { + "External id": 1404271,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696159.115, "dur": 2.619, + "args": { + "External id": 1404272,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696166.155, "dur": 0.456, + "args": { + "External id": 1404273,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696168.350, "dur": 0.494, + "args": { + "External id": 1404274,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696170.508, "dur": 0.531, + "args": { + "External id": 1404275,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696174.504, "dur": 0.284, + "args": { + "External id": 1404276,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696176.539, "dur": 0.690, + "args": { + "External id": 1404277,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696178.496, "dur": 4.246, + "args": { + "External id": 1404278,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696184.408, "dur": 0.344, + "args": { + "External id": 1404279,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696186.235, "dur": 0.404, + "args": { + "External id": 1404280,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530696204.871, "dur": 55.070, + "args": { + "External id": 1404281,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530696297.357, "dur": 147.313, + "args": { + "External id": 1404282,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530696310.304, "dur": 4.258, + "args": { + "External id": 1404283,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530696319.670, "dur": 10.992, + "args": { + "External id": 1404284,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530696324.441, "dur": 5.831, + "args": { + "External id": 1404285,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696328.391, "dur": 0.513, + "args": { + "External id": 1404286,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530696337.597, "dur": 31.733, + "args": { + "External id": 1404287,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696340.226, "dur": 1.865, + "args": { + "External id": 1404288,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696343.998, "dur": 0.417, + "args": { + "External id": 1404289,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696345.981, "dur": 0.426, + "args": { + "External id": 1404290,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696349.909, "dur": 2.275, + "args": { + "External id": 1404291,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696353.631, "dur": 0.593, + "args": { + "External id": 1404292,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696355.571, "dur": 0.307, + "args": { + "External id": 1404293,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696359.064, "dur": 0.608, + "args": { + "External id": 1404294,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696361.397, "dur": 0.522, + "args": { + "External id": 1404295,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530696363.301, "dur": 1.957, + "args": { + "External id": 1404296,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530696388.497, "dur": 46.544, + "args": { + "External id": 1404297,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530696502.443, "dur": 363.794, + "args": { + "External id": 1404298,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530696537.105, "dur": 323.809, + "args": { + "External id": 1404299,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13263, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530696550.075, "dur": 305.045, + "args": { + "External id": 1404300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530696889.352, "dur": 2.503, + "args": { + "External id": 1404301,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13265, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338710, "tid": 2338710, + "ts": 6410530696976.310, "dur": 29808.541, + "args": { + "External id": 1404302,"Record function id": 0, "Ev Idx": 13266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697127.454, "dur": 7.026, + "args": { + "External id": 1404303,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697138.373, "dur": 1.235, + "args": { + "External id": 1404304,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697141.849, "dur": 2.860, + "args": { + "External id": 1404305,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697146.336, "dur": 0.772, + "args": { + "External id": 1404306,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697148.806, "dur": 0.826, + "args": { + "External id": 1404307,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697152.686, "dur": 0.987, + "args": { + "External id": 1404308,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697156.187, "dur": 1.039, + "args": { + "External id": 1404309,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697158.575, "dur": 2.196, + "args": { + "External id": 1404310,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697162.257, "dur": 1.085, + "args": { + "External id": 1404311,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530697167.054, "dur": 0.558, + "args": { + "External id": 1404312,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530697187.453, "dur": 29554.883, + "args": { + "External id": 1404313,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530697203.066, "dur": 29531.650, + "args": { + "External id": 1404314,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530697218.999, "dur": 17.058, + "args": { + "External id": 1404315,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530697239.387, "dur": 29460.723, + "args": { + "External id": 1404316,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530697242.578, "dur": 29456.966, + "args": { + "External id": 1404317,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530697248.374, "dur": 5.766, + "args": { + "External id": 1404318,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530697255.826, "dur": 29440.498, + "args": { + "External id": 1404319,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530726921.232, "dur": 31.340, + "args": { + "External id": 1404320,"Sequence number": 15108873, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13284 + } + }, + { + "ph": "s", "id": 193, "pid": 2338710, "tid": 2338710, "ts": 6410530726921.232, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530726939.517, "dur": 8.394, + "args": { + "External id": 1404321,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530726943.396, "dur": 4.303, + "args": { + "External id": 1404322,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530727017.530, "dur": 111.983, + "args": { + "External id": 1404323,"Record function id": 0, "Ev Idx": 13287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530727132.233, "dur": 1132.721, + "args": { + "External id": 1404324,"Record function id": 0, "Ev Idx": 13288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530727175.450, "dur": 1074.662, + "args": { + "External id": 1404325,"Sequence number": 15108874, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13289 + } + }, + { + "ph": "s", "id": 192, "pid": 2338710, "tid": 2338710, "ts": 6410530727175.450, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530727243.692, "dur": 51.048, + "args": { + "External id": 1404326,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530727307.187, "dur": 102.220, + "args": { + "External id": 1404327,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530727438.025, "dur": 43.157, + "args": { + "External id": 1404328,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530727492.000, "dur": 30.902, + "args": { + "External id": 1404329,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530727550.059, "dur": 29.778, + "args": { + "External id": 1404330,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530727600.500, "dur": 18.407, + "args": { + "External id": 1404331,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530727641.238, "dur": 131.934, + "args": { + "External id": 1404332,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530727691.660, "dur": 11.961, + "args": { + "External id": 1404333,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530727696.919, "dur": 5.811, + "args": { + "External id": 1404334,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530727706.691, "dur": 3.291, + "args": { + "External id": 1404335,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530727711.301, "dur": 1.063, + "args": { + "External id": 1404336,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530727715.240, "dur": 5.237, + "args": { + "External id": 1404337,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530727783.083, "dur": 50.704, + "args": { + "External id": 1404338,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530727866.539, "dur": 28.971, + "args": { + "External id": 1404339,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530727906.274, "dur": 42.406, + "args": { + "External id": 1404340,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530727956.780, "dur": 35.012, + "args": { + "External id": 1404341,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530728014.636, "dur": 25.110, + "args": { + "External id": 1404342,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530728047.265, "dur": 88.017, + "args": { + "External id": 1404343,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530728158.343, "dur": 20.027, + "args": { + "External id": 1404344,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13308 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.15)", "pid": 2338710, "tid": 2338710, + "ts": 6410530728331.541, "dur": 81.148, + "args": { + "External id": 1404345,"Record function id": 0, "Ev Idx": 13309 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530728507.137, "dur": 49.338, + "args": { + "External id": 1404346,"Record function id": 0, "Ev Idx": 13310 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 2338710, "tid": 2338710, + "ts": 6410530728566.133, "dur": 31671.655, + "args": { + "External id": 1404347,"Record function id": 0, "Ev Idx": 13311 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338710, "tid": 2338710, + "ts": 6410530728573.494, "dur": 957.192, + "args": { + "External id": 1404348,"Record function id": 0, "Ev Idx": 13312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530728658.727, "dur": 9.741, + "args": { + "External id": 1404349,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530728681.345, "dur": 39.290, + "args": { + "External id": 1404350,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728687.685, "dur": 2.410, + "args": { + "External id": 1404351,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728694.461, "dur": 0.471, + "args": { + "External id": 1404352,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728696.795, "dur": 0.641, + "args": { + "External id": 1404353,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728699.105, "dur": 0.570, + "args": { + "External id": 1404354,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728702.521, "dur": 0.565, + "args": { + "External id": 1404355,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728704.779, "dur": 0.576, + "args": { + "External id": 1404356,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728706.911, "dur": 3.992, + "args": { + "External id": 1404357,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728712.528, "dur": 0.413, + "args": { + "External id": 1404358,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728714.548, "dur": 0.460, + "args": { + "External id": 1404359,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530728734.023, "dur": 52.941, + "args": { + "External id": 1404360,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530728820.485, "dur": 125.797, + "args": { + "External id": 1404361,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530728832.660, "dur": 4.979, + "args": { + "External id": 1404362,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530728844.735, "dur": 11.500, + "args": { + "External id": 1404363,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530728849.464, "dur": 6.401, + "args": { + "External id": 1404364,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728853.611, "dur": 0.764, + "args": { + "External id": 1404365,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530728863.143, "dur": 30.139, + "args": { + "External id": 1404366,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728865.722, "dur": 0.265, + "args": { + "External id": 1404367,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728867.768, "dur": 2.107, + "args": { + "External id": 1404368,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728871.456, "dur": 0.621, + "args": { + "External id": 1404369,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728873.372, "dur": 2.532, + "args": { + "External id": 1404370,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728879.520, "dur": 0.366, + "args": { + "External id": 1404371,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728881.373, "dur": 0.475, + "args": { + "External id": 1404372,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728883.153, "dur": 0.495, + "args": { + "External id": 1404373,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728886.824, "dur": 0.402, + "args": { + "External id": 1404374,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530728888.667, "dur": 0.506, + "args": { + "External id": 1404375,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530728903.828, "dur": 34.898, + "args": { + "External id": 1404376,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530729000.019, "dur": 408.761, + "args": { + "External id": 1404377,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530729030.950, "dur": 371.817, + "args": { + "External id": 1404378,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13342, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530729041.289, "dur": 355.279, + "args": { + "External id": 1404379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530729450.509, "dur": 3.143, + "args": { + "External id": 1404380,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13344, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338710, "tid": 2338710, + "ts": 6410530729550.663, "dur": 30446.161, + "args": { + "External id": 1404381,"Record function id": 0, "Ev Idx": 13345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729654.611, "dur": 6.925, + "args": { + "External id": 1404382,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729665.141, "dur": 1.063, + "args": { + "External id": 1404383,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729667.883, "dur": 3.476, + "args": { + "External id": 1404384,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729672.892, "dur": 0.989, + "args": { + "External id": 1404385,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729675.050, "dur": 0.995, + "args": { + "External id": 1404386,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729677.423, "dur": 1.098, + "args": { + "External id": 1404387,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729682.634, "dur": 0.927, + "args": { + "External id": 1404388,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729685.419, "dur": 2.429, + "args": { + "External id": 1404389,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729689.410, "dur": 0.940, + "args": { + "External id": 1404390,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530729691.974, "dur": 0.918, + "args": { + "External id": 1404391,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530729713.225, "dur": 30229.993, + "args": { + "External id": 1404392,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530729728.577, "dur": 30204.882, + "args": { + "External id": 1404393,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530729747.057, "dur": 16.497, + "args": { + "External id": 1404394,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530729767.121, "dur": 30125.743, + "args": { + "External id": 1404395,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530729769.883, "dur": 30122.205, + "args": { + "External id": 1404396,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530729776.277, "dur": 4.865, + "args": { + "External id": 1404397,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530729782.783, "dur": 30105.111, + "args": { + "External id": 1404398,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530760175.721, "dur": 35.595, + "args": { + "External id": 1404399,"Sequence number": 15108875, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13363 + } + }, + { + "ph": "s", "id": 191, "pid": 2338710, "tid": 2338710, "ts": 6410530760175.721, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530760195.057, "dur": 11.191, + "args": { + "External id": 1404400,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530760199.782, "dur": 6.056, + "args": { + "External id": 1404401,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530760275.956, "dur": 68.180, + "args": { + "External id": 1404402,"Record function id": 0, "Ev Idx": 13366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530760345.652, "dur": 1185.631, + "args": { + "External id": 1404403,"Record function id": 0, "Ev Idx": 13367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530760387.887, "dur": 1128.862, + "args": { + "External id": 1404404,"Sequence number": 15108876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13368 + } + }, + { + "ph": "s", "id": 190, "pid": 2338710, "tid": 2338710, "ts": 6410530760387.887, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530760467.712, "dur": 52.532, + "args": { + "External id": 1404405,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530760533.560, "dur": 106.024, + "args": { + "External id": 1404406,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530760652.530, "dur": 42.064, + "args": { + "External id": 1404407,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530760704.055, "dur": 31.073, + "args": { + "External id": 1404408,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530760763.655, "dur": 28.714, + "args": { + "External id": 1404409,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530760809.189, "dur": 19.012, + "args": { + "External id": 1404410,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530760850.618, "dur": 133.793, + "args": { + "External id": 1404411,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530760902.404, "dur": 12.122, + "args": { + "External id": 1404412,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530760908.339, "dur": 5.381, + "args": { + "External id": 1404413,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530760917.194, "dur": 4.091, + "args": { + "External id": 1404414,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530760922.756, "dur": 1.072, + "args": { + "External id": 1404415,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530760926.438, "dur": 6.751, + "args": { + "External id": 1404416,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530761015.103, "dur": 101.488, + "args": { + "External id": 1404417,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530761158.221, "dur": 31.480, + "args": { + "External id": 1404418,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530761202.446, "dur": 47.943, + "args": { + "External id": 1404419,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530761259.501, "dur": 36.564, + "args": { + "External id": 1404420,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530761319.683, "dur": 26.841, + "args": { + "External id": 1404421,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530761352.618, "dur": 37.614, + "args": { + "External id": 1404422,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530761409.382, "dur": 35.411, + "args": { + "External id": 1404423,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.16)", "pid": 2338710, "tid": 2338710, + "ts": 6410530761598.232, "dur": 78.511, + "args": { + "External id": 1404424,"Record function id": 0, "Ev Idx": 13388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530761750.350, "dur": 48.288, + "args": { + "External id": 1404425,"Record function id": 0, "Ev Idx": 13389 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 2338710, "tid": 2338710, + "ts": 6410530761807.873, "dur": 30795.768, + "args": { + "External id": 1404426,"Record function id": 0, "Ev Idx": 13390 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338710, "tid": 2338710, + "ts": 6410530761815.682, "dur": 978.673, + "args": { + "External id": 1404427,"Record function id": 0, "Ev Idx": 13391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530761897.351, "dur": 9.118, + "args": { + "External id": 1404428,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530761919.863, "dur": 41.966, + "args": { + "External id": 1404429,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761925.845, "dur": 2.398, + "args": { + "External id": 1404430,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761933.333, "dur": 0.391, + "args": { + "External id": 1404431,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761935.283, "dur": 0.602, + "args": { + "External id": 1404432,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761937.740, "dur": 0.320, + "args": { + "External id": 1404433,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761940.884, "dur": 0.589, + "args": { + "External id": 1404434,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761943.476, "dur": 0.489, + "args": { + "External id": 1404435,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761946.146, "dur": 4.564, + "args": { + "External id": 1404436,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761952.375, "dur": 0.390, + "args": { + "External id": 1404437,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530761954.142, "dur": 0.516, + "args": { + "External id": 1404438,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530761973.101, "dur": 51.572, + "args": { + "External id": 1404439,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530762112.919, "dur": 141.037, + "args": { + "External id": 1404440,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530762125.837, "dur": 6.046, + "args": { + "External id": 1404441,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530762138.036, "dur": 11.263, + "args": { + "External id": 1404442,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530762142.490, "dur": 6.429, + "args": { + "External id": 1404443,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762146.407, "dur": 0.562, + "args": { + "External id": 1404444,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530762158.047, "dur": 31.448, + "args": { + "External id": 1404445,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762160.887, "dur": 2.116, + "args": { + "External id": 1404446,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762164.567, "dur": 0.352, + "args": { + "External id": 1404447,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762166.521, "dur": 0.312, + "args": { + "External id": 1404448,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762170.074, "dur": 2.245, + "args": { + "External id": 1404449,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762173.803, "dur": 0.437, + "args": { + "External id": 1404450,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762175.651, "dur": 0.599, + "args": { + "External id": 1404451,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762179.179, "dur": 0.261, + "args": { + "External id": 1404452,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762181.012, "dur": 0.344, + "args": { + "External id": 1404453,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530762182.904, "dur": 2.034, + "args": { + "External id": 1404454,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530762205.636, "dur": 40.304, + "args": { + "External id": 1404455,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530762311.110, "dur": 380.639, + "args": { + "External id": 1404456,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530762343.659, "dur": 342.323, + "args": { + "External id": 1404457,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13421, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530762354.272, "dur": 325.132, + "args": { + "External id": 1404458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530762718.266, "dur": 2.367, + "args": { + "External id": 1404459,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13423, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338710, "tid": 2338710, + "ts": 6410530762815.958, "dur": 29581.101, + "args": { + "External id": 1404460,"Record function id": 0, "Ev Idx": 13424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762921.168, "dur": 6.413, + "args": { + "External id": 1404461,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762930.790, "dur": 0.869, + "args": { + "External id": 1404462,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762933.750, "dur": 2.946, + "args": { + "External id": 1404463,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762938.409, "dur": 0.832, + "args": { + "External id": 1404464,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762940.488, "dur": 1.059, + "args": { + "External id": 1404465,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762942.791, "dur": 1.045, + "args": { + "External id": 1404466,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762947.788, "dur": 0.846, + "args": { + "External id": 1404467,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762950.283, "dur": 2.348, + "args": { + "External id": 1404468,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762953.988, "dur": 0.711, + "args": { + "External id": 1404469,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530762956.063, "dur": 0.852, + "args": { + "External id": 1404470,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530762977.394, "dur": 29375.765, + "args": { + "External id": 1404471,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530762993.883, "dur": 29350.869, + "args": { + "External id": 1404472,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530763015.130, "dur": 15.337, + "args": { + "External id": 1404473,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530763034.169, "dur": 29275.368, + "args": { + "External id": 1404474,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530763036.760, "dur": 29272.220, + "args": { + "External id": 1404475,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530763042.331, "dur": 5.568, + "args": { + "External id": 1404476,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530763049.740, "dur": 29256.223, + "args": { + "External id": 1404477,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530792547.360, "dur": 30.211, + "args": { + "External id": 1404478,"Sequence number": 15108877, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13442 + } + }, + { + "ph": "s", "id": 189, "pid": 2338710, "tid": 2338710, "ts": 6410530792547.360, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530792564.059, "dur": 8.439, + "args": { + "External id": 1404479,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530792567.777, "dur": 4.396, + "args": { + "External id": 1404480,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530792643.153, "dur": 69.057, + "args": { + "External id": 1404481,"Record function id": 0, "Ev Idx": 13445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530792713.757, "dur": 1170.559, + "args": { + "External id": 1404482,"Record function id": 0, "Ev Idx": 13446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530792754.047, "dur": 1116.073, + "args": { + "External id": 1404483,"Sequence number": 15108878, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13447 + } + }, + { + "ph": "s", "id": 188, "pid": 2338710, "tid": 2338710, "ts": 6410530792754.047, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530792817.013, "dur": 48.927, + "args": { + "External id": 1404484,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530792878.708, "dur": 105.281, + "args": { + "External id": 1404485,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530792994.876, "dur": 38.890, + "args": { + "External id": 1404486,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530793043.804, "dur": 96.957, + "args": { + "External id": 1404487,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530793178.320, "dur": 28.813, + "args": { + "External id": 1404488,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530793229.019, "dur": 19.470, + "args": { + "External id": 1404489,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530793271.864, "dur": 134.851, + "args": { + "External id": 1404490,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530793323.118, "dur": 12.312, + "args": { + "External id": 1404491,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530793328.840, "dur": 5.678, + "args": { + "External id": 1404492,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530793338.348, "dur": 4.385, + "args": { + "External id": 1404493,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530793344.068, "dur": 1.509, + "args": { + "External id": 1404494,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530793348.114, "dur": 5.533, + "args": { + "External id": 1404495,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530793433.340, "dur": 60.347, + "args": { + "External id": 1404496,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530793530.297, "dur": 30.538, + "args": { + "External id": 1404497,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530793572.407, "dur": 44.421, + "args": { + "External id": 1404498,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530793625.207, "dur": 35.701, + "args": { + "External id": 1404499,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530793685.240, "dur": 30.111, + "args": { + "External id": 1404500,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530793723.060, "dur": 36.837, + "args": { + "External id": 1404501,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530793777.860, "dur": 19.822, + "args": { + "External id": 1404502,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13466 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.17)", "pid": 2338710, "tid": 2338710, + "ts": 6410530793948.495, "dur": 80.221, + "args": { + "External id": 1404503,"Record function id": 0, "Ev Idx": 13467 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530794157.776, "dur": 51.215, + "args": { + "External id": 1404504,"Record function id": 0, "Ev Idx": 13468 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 2338710, "tid": 2338710, + "ts": 6410530794218.909, "dur": 31258.055, + "args": { + "External id": 1404505,"Record function id": 0, "Ev Idx": 13469 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338710, "tid": 2338710, + "ts": 6410530794228.018, "dur": 972.038, + "args": { + "External id": 1404506,"Record function id": 0, "Ev Idx": 13470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530794311.237, "dur": 9.888, + "args": { + "External id": 1404507,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530794334.399, "dur": 41.327, + "args": { + "External id": 1404508,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794340.564, "dur": 2.368, + "args": { + "External id": 1404509,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794347.516, "dur": 0.513, + "args": { + "External id": 1404510,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794349.338, "dur": 0.502, + "args": { + "External id": 1404511,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794351.544, "dur": 0.633, + "args": { + "External id": 1404512,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794355.395, "dur": 0.488, + "args": { + "External id": 1404513,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794357.544, "dur": 0.478, + "args": { + "External id": 1404514,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794359.553, "dur": 4.148, + "args": { + "External id": 1404515,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794365.408, "dur": 0.552, + "args": { + "External id": 1404516,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794367.919, "dur": 0.482, + "args": { + "External id": 1404517,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530794387.256, "dur": 78.247, + "args": { + "External id": 1404518,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530794502.400, "dur": 135.769, + "args": { + "External id": 1404519,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530794518.067, "dur": 7.261, + "args": { + "External id": 1404520,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530794532.930, "dur": 11.370, + "args": { + "External id": 1404521,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530794537.577, "dur": 6.330, + "args": { + "External id": 1404522,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794541.456, "dur": 0.714, + "args": { + "External id": 1404523,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530794551.396, "dur": 30.535, + "args": { + "External id": 1404524,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794554.191, "dur": 0.533, + "args": { + "External id": 1404525,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794556.693, "dur": 1.991, + "args": { + "External id": 1404526,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794560.304, "dur": 0.326, + "args": { + "External id": 1404527,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794562.023, "dur": 2.345, + "args": { + "External id": 1404528,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794567.900, "dur": 0.313, + "args": { + "External id": 1404529,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794569.996, "dur": 0.474, + "args": { + "External id": 1404530,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794571.895, "dur": 0.435, + "args": { + "External id": 1404531,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794575.336, "dur": 0.685, + "args": { + "External id": 1404532,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530794577.442, "dur": 0.414, + "args": { + "External id": 1404533,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530794594.766, "dur": 35.440, + "args": { + "External id": 1404534,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530794694.578, "dur": 353.686, + "args": { + "External id": 1404535,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530794726.775, "dur": 316.558, + "args": { + "External id": 1404536,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13500, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530794737.452, "dur": 300.822, + "args": { + "External id": 1404537,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530795121.784, "dur": 4.272, + "args": { + "External id": 1404538,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13502, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338710, "tid": 2338710, + "ts": 6410530795221.034, "dur": 30052.309, + "args": { + "External id": 1404539,"Record function id": 0, "Ev Idx": 13503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795328.239, "dur": 6.966, + "args": { + "External id": 1404540,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795338.851, "dur": 1.098, + "args": { + "External id": 1404541,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795341.928, "dur": 3.354, + "args": { + "External id": 1404542,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795346.807, "dur": 0.961, + "args": { + "External id": 1404543,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795349.113, "dur": 0.946, + "args": { + "External id": 1404544,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795351.285, "dur": 0.777, + "args": { + "External id": 1404545,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795355.738, "dur": 0.960, + "args": { + "External id": 1404546,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795358.467, "dur": 2.233, + "args": { + "External id": 1404547,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795362.515, "dur": 1.023, + "args": { + "External id": 1404548,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530795365.243, "dur": 0.957, + "args": { + "External id": 1404549,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530795387.340, "dur": 29844.203, + "args": { + "External id": 1404550,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530795404.250, "dur": 29819.349, + "args": { + "External id": 1404551,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530795439.198, "dur": 17.896, + "args": { + "External id": 1404552,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530795460.915, "dur": 29727.470, + "args": { + "External id": 1404553,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530795463.400, "dur": 29724.448, + "args": { + "External id": 1404554,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530795469.265, "dur": 5.837, + "args": { + "External id": 1404555,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530795477.034, "dur": 29707.804, + "args": { + "External id": 1404556,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530825409.698, "dur": 41.882, + "args": { + "External id": 1404557,"Sequence number": 15108879, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13521 + } + }, + { + "ph": "s", "id": 187, "pid": 2338710, "tid": 2338710, "ts": 6410530825409.698, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530825437.730, "dur": 8.787, + "args": { + "External id": 1404558,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530825441.376, "dur": 4.783, + "args": { + "External id": 1404559,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530825515.512, "dur": 68.605, + "args": { + "External id": 1404560,"Record function id": 0, "Ev Idx": 13524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530825585.397, "dur": 1144.489, + "args": { + "External id": 1404561,"Record function id": 0, "Ev Idx": 13525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530825626.559, "dur": 1089.976, + "args": { + "External id": 1404562,"Sequence number": 15108880, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13526 + } + }, + { + "ph": "s", "id": 186, "pid": 2338710, "tid": 2338710, "ts": 6410530825626.559, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530825695.751, "dur": 50.417, + "args": { + "External id": 1404563,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530825759.835, "dur": 105.856, + "args": { + "External id": 1404564,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530825878.004, "dur": 39.355, + "args": { + "External id": 1404565,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530825925.684, "dur": 29.034, + "args": { + "External id": 1404566,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530825982.389, "dur": 27.539, + "args": { + "External id": 1404567,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530826027.588, "dur": 20.310, + "args": { + "External id": 1404568,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530826119.768, "dur": 140.207, + "args": { + "External id": 1404569,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530826173.290, "dur": 14.350, + "args": { + "External id": 1404570,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530826179.620, "dur": 7.002, + "args": { + "External id": 1404571,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530826190.621, "dur": 4.894, + "args": { + "External id": 1404572,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530826196.778, "dur": 2.569, + "args": { + "External id": 1404573,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530826201.644, "dur": 4.970, + "args": { + "External id": 1404574,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530826271.032, "dur": 57.100, + "args": { + "External id": 1404575,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530826361.025, "dur": 31.812, + "args": { + "External id": 1404576,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530826404.490, "dur": 61.304, + "args": { + "External id": 1404577,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530826475.688, "dur": 36.669, + "args": { + "External id": 1404578,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530826540.527, "dur": 25.999, + "args": { + "External id": 1404579,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530826572.555, "dur": 37.080, + "args": { + "External id": 1404580,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530826627.515, "dur": 18.787, + "args": { + "External id": 1404581,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13545 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.18)", "pid": 2338710, "tid": 2338710, + "ts": 6410530826795.649, "dur": 81.471, + "args": { + "External id": 1404582,"Record function id": 0, "Ev Idx": 13546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530826951.793, "dur": 49.262, + "args": { + "External id": 1404583,"Record function id": 0, "Ev Idx": 13547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 2338710, "tid": 2338710, + "ts": 6410530827010.742, "dur": 32078.132, + "args": { + "External id": 1404584,"Record function id": 0, "Ev Idx": 13548 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338710, "tid": 2338710, + "ts": 6410530827018.504, "dur": 993.128, + "args": { + "External id": 1404585,"Record function id": 0, "Ev Idx": 13549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530827153.854, "dur": 10.867, + "args": { + "External id": 1404586,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530827178.572, "dur": 38.601, + "args": { + "External id": 1404587,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827184.430, "dur": 2.351, + "args": { + "External id": 1404588,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827191.128, "dur": 0.421, + "args": { + "External id": 1404589,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827193.177, "dur": 0.467, + "args": { + "External id": 1404590,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827195.455, "dur": 0.366, + "args": { + "External id": 1404591,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827199.402, "dur": 0.479, + "args": { + "External id": 1404592,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827201.338, "dur": 0.549, + "args": { + "External id": 1404593,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827203.647, "dur": 3.574, + "args": { + "External id": 1404594,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827208.713, "dur": 0.344, + "args": { + "External id": 1404595,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827210.630, "dur": 0.518, + "args": { + "External id": 1404596,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530827229.275, "dur": 56.358, + "args": { + "External id": 1404597,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530827323.583, "dur": 142.297, + "args": { + "External id": 1404598,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530827335.266, "dur": 3.769, + "args": { + "External id": 1404599,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530827344.197, "dur": 10.275, + "args": { + "External id": 1404600,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530827348.661, "dur": 5.430, + "args": { + "External id": 1404601,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827352.400, "dur": 0.490, + "args": { + "External id": 1404602,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530827362.011, "dur": 30.095, + "args": { + "External id": 1404603,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827364.301, "dur": 2.225, + "args": { + "External id": 1404604,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827368.434, "dur": 0.547, + "args": { + "External id": 1404605,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827370.627, "dur": 0.453, + "args": { + "External id": 1404606,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827373.577, "dur": 2.407, + "args": { + "External id": 1404607,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827377.474, "dur": 0.410, + "args": { + "External id": 1404608,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827379.369, "dur": 0.367, + "args": { + "External id": 1404609,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827382.705, "dur": 0.241, + "args": { + "External id": 1404610,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827384.431, "dur": 0.246, + "args": { + "External id": 1404611,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530827386.210, "dur": 2.020, + "args": { + "External id": 1404612,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530827406.459, "dur": 49.558, + "args": { + "External id": 1404613,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530827522.112, "dur": 395.064, + "args": { + "External id": 1404614,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530827554.793, "dur": 357.402, + "args": { + "External id": 1404615,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13579, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530827565.088, "dur": 341.556, + "args": { + "External id": 1404616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530827940.562, "dur": 2.213, + "args": { + "External id": 1404617,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13581, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338710, "tid": 2338710, + "ts": 6410530828032.825, "dur": 30816.014, + "args": { + "External id": 1404618,"Record function id": 0, "Ev Idx": 13582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828192.735, "dur": 7.267, + "args": { + "External id": 1404619,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828218.457, "dur": 0.959, + "args": { + "External id": 1404620,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828221.380, "dur": 3.462, + "args": { + "External id": 1404621,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828228.467, "dur": 0.844, + "args": { + "External id": 1404622,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828230.578, "dur": 0.724, + "args": { + "External id": 1404623,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828232.469, "dur": 0.852, + "args": { + "External id": 1404624,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828234.917, "dur": 1.051, + "args": { + "External id": 1404625,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828239.646, "dur": 2.064, + "args": { + "External id": 1404626,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828243.084, "dur": 1.090, + "args": { + "External id": 1404627,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530828245.749, "dur": 0.777, + "args": { + "External id": 1404628,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530828267.306, "dur": 30529.102, + "args": { + "External id": 1404629,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530828283.935, "dur": 30502.257, + "args": { + "External id": 1404630,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530828298.570, "dur": 17.539, + "args": { + "External id": 1404631,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530828321.729, "dur": 30423.927, + "args": { + "External id": 1404632,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530828324.327, "dur": 30420.523, + "args": { + "External id": 1404633,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530828330.246, "dur": 5.895, + "args": { + "External id": 1404634,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530828337.963, "dur": 30403.385, + "args": { + "External id": 1404635,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530858997.497, "dur": 35.615, + "args": { + "External id": 1404636,"Sequence number": 15108881, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13600 + } + }, + { + "ph": "s", "id": 185, "pid": 2338710, "tid": 2338710, "ts": 6410530858997.497, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530859017.590, "dur": 10.864, + "args": { + "External id": 1404637,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530859022.132, "dur": 6.064, + "args": { + "External id": 1404638,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530859130.328, "dur": 71.451, + "args": { + "External id": 1404639,"Record function id": 0, "Ev Idx": 13603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530859203.590, "dur": 1133.647, + "args": { + "External id": 1404640,"Record function id": 0, "Ev Idx": 13604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530859244.156, "dur": 1079.280, + "args": { + "External id": 1404641,"Sequence number": 15108882, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13605 + } + }, + { + "ph": "s", "id": 184, "pid": 2338710, "tid": 2338710, "ts": 6410530859244.156, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530859318.988, "dur": 51.069, + "args": { + "External id": 1404642,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530859382.658, "dur": 119.872, + "args": { + "External id": 1404643,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530859517.521, "dur": 40.314, + "args": { + "External id": 1404644,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530859567.041, "dur": 29.383, + "args": { + "External id": 1404645,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530859622.062, "dur": 28.616, + "args": { + "External id": 1404646,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530859672.681, "dur": 16.283, + "args": { + "External id": 1404647,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530859710.824, "dur": 132.952, + "args": { + "External id": 1404648,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530859762.277, "dur": 12.488, + "args": { + "External id": 1404649,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530859768.057, "dur": 5.859, + "args": { + "External id": 1404650,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530859777.721, "dur": 4.272, + "args": { + "External id": 1404651,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530859783.358, "dur": 1.733, + "args": { + "External id": 1404652,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530859787.423, "dur": 4.649, + "args": { + "External id": 1404653,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530859854.901, "dur": 48.237, + "args": { + "External id": 1404654,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530859931.944, "dur": 28.073, + "args": { + "External id": 1404655,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530859969.918, "dur": 42.520, + "args": { + "External id": 1404656,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530860021.618, "dur": 79.690, + "args": { + "External id": 1404657,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530860130.908, "dur": 28.470, + "args": { + "External id": 1404658,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530860167.845, "dur": 40.873, + "args": { + "External id": 1404659,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530860230.057, "dur": 18.752, + "args": { + "External id": 1404660,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13624 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.19)", "pid": 2338710, "tid": 2338710, + "ts": 6410530860404.630, "dur": 93.495, + "args": { + "External id": 1404661,"Record function id": 0, "Ev Idx": 13625 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530860573.828, "dur": 47.089, + "args": { + "External id": 1404662,"Record function id": 0, "Ev Idx": 13626 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 2338710, "tid": 2338710, + "ts": 6410530860630.748, "dur": 32036.936, + "args": { + "External id": 1404663,"Record function id": 0, "Ev Idx": 13627 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338710, "tid": 2338710, + "ts": 6410530860638.559, "dur": 955.719, + "args": { + "External id": 1404664,"Record function id": 0, "Ev Idx": 13628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530860721.071, "dur": 9.471, + "args": { + "External id": 1404665,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530860744.003, "dur": 34.956, + "args": { + "External id": 1404666,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860750.018, "dur": 2.245, + "args": { + "External id": 1404667,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860756.426, "dur": 0.538, + "args": { + "External id": 1404668,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860758.292, "dur": 0.622, + "args": { + "External id": 1404669,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860760.589, "dur": 0.362, + "args": { + "External id": 1404670,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860763.611, "dur": 0.456, + "args": { + "External id": 1404671,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860765.526, "dur": 0.388, + "args": { + "External id": 1404672,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860767.260, "dur": 2.211, + "args": { + "External id": 1404673,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860770.781, "dur": 0.351, + "args": { + "External id": 1404674,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860772.601, "dur": 0.565, + "args": { + "External id": 1404675,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530860789.911, "dur": 55.093, + "args": { + "External id": 1404676,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530860877.632, "dur": 130.189, + "args": { + "External id": 1404677,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530860889.247, "dur": 4.619, + "args": { + "External id": 1404678,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530860901.468, "dur": 10.464, + "args": { + "External id": 1404679,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530860905.760, "dur": 5.790, + "args": { + "External id": 1404680,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860909.806, "dur": 0.562, + "args": { + "External id": 1404681,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530860919.673, "dur": 34.265, + "args": { + "External id": 1404682,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860922.248, "dur": 1.893, + "args": { + "External id": 1404683,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860925.922, "dur": 0.587, + "args": { + "External id": 1404684,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860932.026, "dur": 0.354, + "args": { + "External id": 1404685,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860935.514, "dur": 2.438, + "args": { + "External id": 1404686,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860939.492, "dur": 0.218, + "args": { + "External id": 1404687,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860941.197, "dur": 1.887, + "args": { + "External id": 1404688,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860944.307, "dur": 0.277, + "args": { + "External id": 1404689,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860946.174, "dur": 0.521, + "args": { + "External id": 1404690,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530860949.347, "dur": 0.586, + "args": { + "External id": 1404691,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530860965.293, "dur": 35.081, + "args": { + "External id": 1404692,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530861111.556, "dur": 378.139, + "args": { + "External id": 1404693,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530861143.965, "dur": 340.064, + "args": { + "External id": 1404694,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13658, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530861155.432, "dur": 320.651, + "args": { + "External id": 1404695,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530861515.634, "dur": 2.697, + "args": { + "External id": 1404696,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13660, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338710, "tid": 2338710, + "ts": 6410530861616.122, "dur": 30853.732, + "args": { + "External id": 1404697,"Record function id": 0, "Ev Idx": 13661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861725.958, "dur": 6.841, + "args": { + "External id": 1404698,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861736.515, "dur": 1.025, + "args": { + "External id": 1404699,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861739.215, "dur": 3.551, + "args": { + "External id": 1404700,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861744.561, "dur": 0.696, + "args": { + "External id": 1404701,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861746.886, "dur": 1.100, + "args": { + "External id": 1404702,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861749.255, "dur": 0.930, + "args": { + "External id": 1404703,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861753.695, "dur": 0.650, + "args": { + "External id": 1404704,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861755.675, "dur": 1.785, + "args": { + "External id": 1404705,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861759.296, "dur": 1.045, + "args": { + "External id": 1404706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530861761.833, "dur": 0.742, + "args": { + "External id": 1404707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530861783.295, "dur": 30641.459, + "args": { + "External id": 1404708,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530861798.477, "dur": 30609.518, + "args": { + "External id": 1404709,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530861818.559, "dur": 16.261, + "args": { + "External id": 1404710,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530861838.381, "dur": 30535.060, + "args": { + "External id": 1404711,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530861840.682, "dur": 30532.128, + "args": { + "External id": 1404712,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530861846.128, "dur": 5.016, + "args": { + "External id": 1404713,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530861852.857, "dur": 30516.253, + "args": { + "External id": 1404714,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530892606.974, "dur": 35.382, + "args": { + "External id": 1404715,"Sequence number": 15108883, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13679 + } + }, + { + "ph": "s", "id": 183, "pid": 2338710, "tid": 2338710, "ts": 6410530892606.974, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530892628.455, "dur": 8.703, + "args": { + "External id": 1404716,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530892632.342, "dur": 4.596, + "args": { + "External id": 1404717,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530892707.776, "dur": 68.422, + "args": { + "External id": 1404718,"Record function id": 0, "Ev Idx": 13682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530892777.529, "dur": 1160.238, + "args": { + "External id": 1404719,"Record function id": 0, "Ev Idx": 13683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530892816.977, "dur": 1106.840, + "args": { + "External id": 1404720,"Sequence number": 15108884, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13684 + } + }, + { + "ph": "s", "id": 182, "pid": 2338710, "tid": 2338710, "ts": 6410530892816.977, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530892879.772, "dur": 49.284, + "args": { + "External id": 1404721,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530892942.423, "dur": 105.979, + "args": { + "External id": 1404722,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530893125.267, "dur": 50.774, + "args": { + "External id": 1404723,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530893186.625, "dur": 38.495, + "args": { + "External id": 1404724,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530893256.647, "dur": 29.571, + "args": { + "External id": 1404725,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530893304.643, "dur": 16.754, + "args": { + "External id": 1404726,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530893345.163, "dur": 154.308, + "args": { + "External id": 1404727,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530893396.261, "dur": 12.813, + "args": { + "External id": 1404728,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530893402.354, "dur": 5.876, + "args": { + "External id": 1404729,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530893412.127, "dur": 19.220, + "args": { + "External id": 1404730,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530893433.892, "dur": 1.751, + "args": { + "External id": 1404731,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530893439.727, "dur": 5.487, + "args": { + "External id": 1404732,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530893511.401, "dur": 53.553, + "args": { + "External id": 1404733,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530893598.016, "dur": 29.128, + "args": { + "External id": 1404734,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530893638.533, "dur": 43.286, + "args": { + "External id": 1404735,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530893688.243, "dur": 34.945, + "args": { + "External id": 1404736,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530893748.231, "dur": 26.096, + "args": { + "External id": 1404737,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530893780.201, "dur": 36.905, + "args": { + "External id": 1404738,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530893836.438, "dur": 18.376, + "args": { + "External id": 1404739,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13703 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.20)", "pid": 2338710, "tid": 2338710, + "ts": 6410530894005.525, "dur": 130.303, + "args": { + "External id": 1404740,"Record function id": 0, "Ev Idx": 13704 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530894218.445, "dur": 48.282, + "args": { + "External id": 1404741,"Record function id": 0, "Ev Idx": 13705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 2338710, "tid": 2338710, + "ts": 6410530894276.407, "dur": 34741.043, + "args": { + "External id": 1404742,"Record function id": 0, "Ev Idx": 13706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338710, "tid": 2338710, + "ts": 6410530894285.261, "dur": 980.526, + "args": { + "External id": 1404743,"Record function id": 0, "Ev Idx": 13707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530894369.718, "dur": 10.197, + "args": { + "External id": 1404744,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530894392.867, "dur": 54.943, + "args": { + "External id": 1404745,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894399.298, "dur": 2.450, + "args": { + "External id": 1404746,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894406.448, "dur": 0.553, + "args": { + "External id": 1404747,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894408.543, "dur": 0.537, + "args": { + "External id": 1404748,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894410.786, "dur": 0.500, + "args": { + "External id": 1404749,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894414.038, "dur": 15.079, + "args": { + "External id": 1404750,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894432.034, "dur": 0.404, + "args": { + "External id": 1404751,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894433.751, "dur": 3.434, + "args": { + "External id": 1404752,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894438.917, "dur": 0.381, + "args": { + "External id": 1404753,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894441.058, "dur": 0.413, + "args": { + "External id": 1404754,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530894460.535, "dur": 56.995, + "args": { + "External id": 1404755,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530894553.045, "dur": 128.178, + "args": { + "External id": 1404756,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530894564.731, "dur": 5.139, + "args": { + "External id": 1404757,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530894575.105, "dur": 10.605, + "args": { + "External id": 1404758,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530894579.612, "dur": 5.725, + "args": { + "External id": 1404759,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894583.645, "dur": 0.440, + "args": { + "External id": 1404760,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530894593.727, "dur": 30.362, + "args": { + "External id": 1404761,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894596.410, "dur": 1.941, + "args": { + "External id": 1404762,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894599.912, "dur": 0.404, + "args": { + "External id": 1404763,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894601.813, "dur": 0.604, + "args": { + "External id": 1404764,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894605.299, "dur": 2.138, + "args": { + "External id": 1404765,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894609.303, "dur": 0.383, + "args": { + "External id": 1404766,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894611.007, "dur": 0.312, + "args": { + "External id": 1404767,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894613.961, "dur": 0.682, + "args": { + "External id": 1404768,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894616.288, "dur": 0.592, + "args": { + "External id": 1404769,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530894618.760, "dur": 1.770, + "args": { + "External id": 1404770,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530894639.630, "dur": 34.027, + "args": { + "External id": 1404771,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530894743.190, "dur": 416.523, + "args": { + "External id": 1404772,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530894777.137, "dur": 376.823, + "args": { + "External id": 1404773,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13737, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530894787.977, "dur": 359.399, + "args": { + "External id": 1404774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530895188.070, "dur": 2.463, + "args": { + "External id": 1404775,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13739, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338710, "tid": 2338710, + "ts": 6410530895287.067, "dur": 33541.414, + "args": { + "External id": 1404776,"Record function id": 0, "Ev Idx": 13740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895393.026, "dur": 6.761, + "args": { + "External id": 1404777,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895403.473, "dur": 1.234, + "args": { + "External id": 1404778,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895406.231, "dur": 3.046, + "args": { + "External id": 1404779,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895410.894, "dur": 1.258, + "args": { + "External id": 1404780,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895413.356, "dur": 0.979, + "args": { + "External id": 1404781,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895431.389, "dur": 1.431, + "args": { + "External id": 1404782,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895434.950, "dur": 1.097, + "args": { + "External id": 1404783,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895437.819, "dur": 1.779, + "args": { + "External id": 1404784,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895443.126, "dur": 0.930, + "args": { + "External id": 1404785,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530895445.537, "dur": 0.990, + "args": { + "External id": 1404786,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530895466.761, "dur": 33320.003, + "args": { + "External id": 1404787,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530895483.395, "dur": 33295.321, + "args": { + "External id": 1404788,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530895504.299, "dur": 16.507, + "args": { + "External id": 1404789,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530895524.381, "dur": 33220.511, + "args": { + "External id": 1404790,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530895526.848, "dur": 33217.484, + "args": { + "External id": 1404791,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530895532.841, "dur": 6.235, + "args": { + "External id": 1404792,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530895543.510, "dur": 33197.639, + "args": { + "External id": 1404793,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530928962.816, "dur": 30.923, + "args": { + "External id": 1404794,"Sequence number": 15108885, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13758 + } + }, + { + "ph": "s", "id": 181, "pid": 2338710, "tid": 2338710, "ts": 6410530928962.816, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530928980.792, "dur": 8.372, + "args": { + "External id": 1404795,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530928984.576, "dur": 4.383, + "args": { + "External id": 1404796,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530929083.866, "dur": 71.073, + "args": { + "External id": 1404797,"Record function id": 0, "Ev Idx": 13761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530929156.977, "dur": 1112.620, + "args": { + "External id": 1404798,"Record function id": 0, "Ev Idx": 13762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530929197.258, "dur": 1058.311, + "args": { + "External id": 1404799,"Sequence number": 15108886, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13763 + } + }, + { + "ph": "s", "id": 180, "pid": 2338710, "tid": 2338710, "ts": 6410530929197.258, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530929266.569, "dur": 47.112, + "args": { + "External id": 1404800,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530929326.602, "dur": 108.299, + "args": { + "External id": 1404801,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530929449.709, "dur": 43.418, + "args": { + "External id": 1404802,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530929503.553, "dur": 30.101, + "args": { + "External id": 1404803,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530929558.146, "dur": 26.637, + "args": { + "External id": 1404804,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530929607.172, "dur": 15.866, + "args": { + "External id": 1404805,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530929644.903, "dur": 130.538, + "args": { + "External id": 1404806,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530929694.932, "dur": 12.239, + "args": { + "External id": 1404807,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530929701.186, "dur": 5.274, + "args": { + "External id": 1404808,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530929709.992, "dur": 4.238, + "args": { + "External id": 1404809,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530929715.666, "dur": 1.000, + "args": { + "External id": 1404810,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530929719.286, "dur": 5.420, + "args": { + "External id": 1404811,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530929786.019, "dur": 48.171, + "args": { + "External id": 1404812,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530929866.645, "dur": 28.769, + "args": { + "External id": 1404813,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530929905.849, "dur": 43.726, + "args": { + "External id": 1404814,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530929958.004, "dur": 35.225, + "args": { + "External id": 1404815,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530930014.679, "dur": 24.322, + "args": { + "External id": 1404816,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530930046.204, "dur": 89.335, + "args": { + "External id": 1404817,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530930160.143, "dur": 20.658, + "args": { + "External id": 1404818,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13782 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.21)", "pid": 2338710, "tid": 2338710, + "ts": 6410530930334.729, "dur": 78.839, + "args": { + "External id": 1404819,"Record function id": 0, "Ev Idx": 13783 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530930506.875, "dur": 49.357, + "args": { + "External id": 1404820,"Record function id": 0, "Ev Idx": 13784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 2338710, "tid": 2338710, + "ts": 6410530930565.788, "dur": 32039.752, + "args": { + "External id": 1404821,"Record function id": 0, "Ev Idx": 13785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338710, "tid": 2338710, + "ts": 6410530930575.610, "dur": 952.595, + "args": { + "External id": 1404822,"Record function id": 0, "Ev Idx": 13786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530930660.022, "dur": 9.287, + "args": { + "External id": 1404823,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530930682.462, "dur": 39.077, + "args": { + "External id": 1404824,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930688.454, "dur": 2.171, + "args": { + "External id": 1404825,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930694.544, "dur": 0.525, + "args": { + "External id": 1404826,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930696.653, "dur": 0.552, + "args": { + "External id": 1404827,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930698.878, "dur": 0.552, + "args": { + "External id": 1404828,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930702.151, "dur": 0.585, + "args": { + "External id": 1404829,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930704.327, "dur": 0.595, + "args": { + "External id": 1404830,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930706.652, "dur": 3.897, + "args": { + "External id": 1404831,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930712.352, "dur": 0.697, + "args": { + "External id": 1404832,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930714.547, "dur": 0.549, + "args": { + "External id": 1404833,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530930733.399, "dur": 53.229, + "args": { + "External id": 1404834,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530930820.311, "dur": 125.848, + "args": { + "External id": 1404835,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530930831.030, "dur": 4.614, + "args": { + "External id": 1404836,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530930840.719, "dur": 10.300, + "args": { + "External id": 1404837,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530930845.282, "dur": 5.321, + "args": { + "External id": 1404838,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930848.890, "dur": 0.505, + "args": { + "External id": 1404839,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530930858.156, "dur": 33.270, + "args": { + "External id": 1404840,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930860.963, "dur": 1.469, + "args": { + "External id": 1404841,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930864.179, "dur": 0.640, + "args": { + "External id": 1404842,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930866.484, "dur": 0.438, + "args": { + "External id": 1404843,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930869.356, "dur": 2.697, + "args": { + "External id": 1404844,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930873.636, "dur": 0.440, + "args": { + "External id": 1404845,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930875.805, "dur": 0.503, + "args": { + "External id": 1404846,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930879.252, "dur": 0.633, + "args": { + "External id": 1404847,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930881.435, "dur": 0.576, + "args": { + "External id": 1404848,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530930886.543, "dur": 1.213, + "args": { + "External id": 1404849,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530930903.992, "dur": 34.823, + "args": { + "External id": 1404850,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530931000.064, "dur": 407.605, + "args": { + "External id": 1404851,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530931031.493, "dur": 370.644, + "args": { + "External id": 1404852,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13816, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530931041.446, "dur": 354.854, + "args": { + "External id": 1404853,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530931450.022, "dur": 3.287, + "args": { + "External id": 1404854,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13818, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338710, "tid": 2338710, + "ts": 6410530931549.583, "dur": 30831.317, + "args": { + "External id": 1404855,"Record function id": 0, "Ev Idx": 13819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931654.347, "dur": 6.699, + "args": { + "External id": 1404856,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931664.302, "dur": 1.056, + "args": { + "External id": 1404857,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931666.938, "dur": 3.080, + "args": { + "External id": 1404858,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931671.508, "dur": 1.068, + "args": { + "External id": 1404859,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931673.718, "dur": 1.035, + "args": { + "External id": 1404860,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931676.039, "dur": 0.919, + "args": { + "External id": 1404861,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931678.656, "dur": 1.012, + "args": { + "External id": 1404862,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931681.405, "dur": 1.937, + "args": { + "External id": 1404863,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931684.659, "dur": 0.772, + "args": { + "External id": 1404864,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530931688.523, "dur": 0.804, + "args": { + "External id": 1404865,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530931707.687, "dur": 30620.744, + "args": { + "External id": 1404866,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530931730.998, "dur": 30587.600, + "args": { + "External id": 1404867,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530931747.324, "dur": 15.626, + "args": { + "External id": 1404868,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530931766.842, "dur": 30508.749, + "args": { + "External id": 1404869,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530931769.377, "dur": 30505.479, + "args": { + "External id": 1404870,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530931775.233, "dur": 5.394, + "args": { + "External id": 1404871,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530931782.286, "dur": 30488.765, + "args": { + "External id": 1404872,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530962543.310, "dur": 34.875, + "args": { + "External id": 1404873,"Sequence number": 15108887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13837 + } + }, + { + "ph": "s", "id": 179, "pid": 2338710, "tid": 2338710, "ts": 6410530962543.310, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530962562.501, "dur": 10.610, + "args": { + "External id": 1404874,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530962567.174, "dur": 5.550, + "args": { + "External id": 1404875,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530962647.172, "dur": 70.864, + "args": { + "External id": 1404876,"Record function id": 0, "Ev Idx": 13840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530962719.387, "dur": 1168.532, + "args": { + "External id": 1404877,"Record function id": 0, "Ev Idx": 13841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530962758.160, "dur": 1116.312, + "args": { + "External id": 1404878,"Sequence number": 15108888, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13842 + } + }, + { + "ph": "s", "id": 178, "pid": 2338710, "tid": 2338710, "ts": 6410530962758.160, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530962827.276, "dur": 51.847, + "args": { + "External id": 1404879,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530962892.003, "dur": 111.186, + "args": { + "External id": 1404880,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530963014.245, "dur": 89.554, + "args": { + "External id": 1404881,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530963116.811, "dur": 36.331, + "args": { + "External id": 1404882,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530963183.218, "dur": 29.838, + "args": { + "External id": 1404883,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530963232.314, "dur": 17.615, + "args": { + "External id": 1404884,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530963272.301, "dur": 135.759, + "args": { + "External id": 1404885,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530963322.879, "dur": 13.207, + "args": { + "External id": 1404886,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530963329.110, "dur": 5.917, + "args": { + "External id": 1404887,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530963338.996, "dur": 4.538, + "args": { + "External id": 1404888,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530963344.966, "dur": 1.036, + "args": { + "External id": 1404889,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530963348.669, "dur": 4.077, + "args": { + "External id": 1404890,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530963433.605, "dur": 67.682, + "args": { + "External id": 1404891,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530963536.330, "dur": 31.224, + "args": { + "External id": 1404892,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530963577.040, "dur": 43.826, + "args": { + "External id": 1404893,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530963630.440, "dur": 35.290, + "args": { + "External id": 1404894,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530963687.474, "dur": 28.969, + "args": { + "External id": 1404895,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530963723.088, "dur": 37.013, + "args": { + "External id": 1404896,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530963780.143, "dur": 20.751, + "args": { + "External id": 1404897,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13861 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.22)", "pid": 2338710, "tid": 2338710, + "ts": 6410530963955.533, "dur": 75.111, + "args": { + "External id": 1404898,"Record function id": 0, "Ev Idx": 13862 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530964158.601, "dur": 50.198, + "args": { + "External id": 1404899,"Record function id": 0, "Ev Idx": 13863 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 2338710, "tid": 2338710, + "ts": 6410530964219.281, "dur": 31507.360, + "args": { + "External id": 1404900,"Record function id": 0, "Ev Idx": 13864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338710, "tid": 2338710, + "ts": 6410530964227.442, "dur": 995.868, + "args": { + "External id": 1404901,"Record function id": 0, "Ev Idx": 13865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530964311.587, "dur": 10.335, + "args": { + "External id": 1404902,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530964335.372, "dur": 37.944, + "args": { + "External id": 1404903,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964341.460, "dur": 2.177, + "args": { + "External id": 1404904,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964347.496, "dur": 0.624, + "args": { + "External id": 1404905,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964349.722, "dur": 0.639, + "args": { + "External id": 1404906,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964352.252, "dur": 0.667, + "args": { + "External id": 1404907,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964355.650, "dur": 0.366, + "args": { + "External id": 1404908,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964357.591, "dur": 0.613, + "args": { + "External id": 1404909,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964359.851, "dur": 3.651, + "args": { + "External id": 1404910,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964365.535, "dur": 0.246, + "args": { + "External id": 1404911,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964367.404, "dur": 0.261, + "args": { + "External id": 1404912,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530964385.123, "dur": 72.556, + "args": { + "External id": 1404913,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530964494.472, "dur": 153.511, + "args": { + "External id": 1404914,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530964506.510, "dur": 5.228, + "args": { + "External id": 1404915,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530964517.276, "dur": 11.032, + "args": { + "External id": 1404916,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530964521.875, "dur": 6.046, + "args": { + "External id": 1404917,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964525.757, "dur": 0.714, + "args": { + "External id": 1404918,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530964535.690, "dur": 29.820, + "args": { + "External id": 1404919,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964538.622, "dur": 1.671, + "args": { + "External id": 1404920,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964541.727, "dur": 0.734, + "args": { + "External id": 1404921,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964543.800, "dur": 0.550, + "args": { + "External id": 1404922,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964547.556, "dur": 1.844, + "args": { + "External id": 1404923,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964551.249, "dur": 0.547, + "args": { + "External id": 1404924,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964553.432, "dur": 0.711, + "args": { + "External id": 1404925,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964556.308, "dur": 0.470, + "args": { + "External id": 1404926,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964558.181, "dur": 0.515, + "args": { + "External id": 1404927,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530964560.320, "dur": 1.336, + "args": { + "External id": 1404928,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530964601.524, "dur": 38.615, + "args": { + "External id": 1404929,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530964705.634, "dur": 408.259, + "args": { + "External id": 1404930,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530964738.944, "dur": 369.236, + "args": { + "External id": 1404931,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13895, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530964750.373, "dur": 349.586, + "args": { + "External id": 1404932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530965142.408, "dur": 2.995, + "args": { + "External id": 1404933,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13897, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338710, "tid": 2338710, + "ts": 6410530965246.670, "dur": 30281.242, + "args": { + "External id": 1404934,"Record function id": 0, "Ev Idx": 13898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965356.875, "dur": 7.162, + "args": { + "External id": 1404935,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965367.330, "dur": 1.426, + "args": { + "External id": 1404936,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965370.447, "dur": 3.220, + "args": { + "External id": 1404937,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965375.335, "dur": 0.874, + "args": { + "External id": 1404938,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965377.530, "dur": 0.719, + "args": { + "External id": 1404939,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965379.583, "dur": 1.032, + "args": { + "External id": 1404940,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965382.177, "dur": 0.887, + "args": { + "External id": 1404941,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965385.077, "dur": 2.264, + "args": { + "External id": 1404942,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965388.743, "dur": 1.129, + "args": { + "External id": 1404943,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530965393.387, "dur": 0.757, + "args": { + "External id": 1404944,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530965412.469, "dur": 30072.297, + "args": { + "External id": 1404945,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530965445.206, "dur": 30031.216, + "args": { + "External id": 1404946,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530965469.333, "dur": 15.691, + "args": { + "External id": 1404947,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530965488.641, "dur": 29948.748, + "args": { + "External id": 1404948,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530965491.444, "dur": 29945.345, + "args": { + "External id": 1404949,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530965497.248, "dur": 6.000, + "args": { + "External id": 1404950,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530965505.055, "dur": 29928.438, + "args": { + "External id": 1404951,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530995668.721, "dur": 32.614, + "args": { + "External id": 1404952,"Sequence number": 15108889, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13916 + } + }, + { + "ph": "s", "id": 177, "pid": 2338710, "tid": 2338710, "ts": 6410530995668.721, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410530995687.181, "dur": 9.123, + "args": { + "External id": 1404953,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530995691.674, "dur": 4.410, + "args": { + "External id": 1404954,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410530995765.683, "dur": 69.875, + "args": { + "External id": 1404955,"Record function id": 0, "Ev Idx": 13919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410530995836.997, "dur": 1134.567, + "args": { + "External id": 1404956,"Record function id": 0, "Ev Idx": 13920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410530995878.030, "dur": 1080.454, + "args": { + "External id": 1404957,"Sequence number": 15108890, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13921 + } + }, + { + "ph": "s", "id": 176, "pid": 2338710, "tid": 2338710, "ts": 6410530995878.030, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530995948.753, "dur": 47.095, + "args": { + "External id": 1404958,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530996007.777, "dur": 146.168, + "args": { + "External id": 1404959,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530996170.405, "dur": 43.373, + "args": { + "External id": 1404960,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530996222.723, "dur": 30.977, + "args": { + "External id": 1404961,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530996281.547, "dur": 29.292, + "args": { + "External id": 1404962,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410530996331.313, "dur": 18.416, + "args": { + "External id": 1404963,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410530996371.531, "dur": 150.825, + "args": { + "External id": 1404964,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410530996436.742, "dur": 13.262, + "args": { + "External id": 1404965,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530996442.554, "dur": 6.437, + "args": { + "External id": 1404966,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530996452.640, "dur": 4.295, + "args": { + "External id": 1404967,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530996458.286, "dur": 1.441, + "args": { + "External id": 1404968,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530996462.480, "dur": 4.694, + "args": { + "External id": 1404969,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530996533.544, "dur": 55.026, + "args": { + "External id": 1404970,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410530996621.146, "dur": 33.021, + "args": { + "External id": 1404971,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530996663.969, "dur": 43.708, + "args": { + "External id": 1404972,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530996716.966, "dur": 36.226, + "args": { + "External id": 1404973,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410530996775.027, "dur": 27.879, + "args": { + "External id": 1404974,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410530996810.056, "dur": 36.436, + "args": { + "External id": 1404975,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410530996867.003, "dur": 18.647, + "args": { + "External id": 1404976,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.23)", "pid": 2338710, "tid": 2338710, + "ts": 6410530997037.312, "dur": 128.176, + "args": { + "External id": 1404977,"Record function id": 0, "Ev Idx": 13941 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410530997245.966, "dur": 50.000, + "args": { + "External id": 1404978,"Record function id": 0, "Ev Idx": 13942 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 2338710, "tid": 2338710, + "ts": 6410530997305.544, "dur": 32266.825, + "args": { + "External id": 1404979,"Record function id": 0, "Ev Idx": 13943 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338710, "tid": 2338710, + "ts": 6410530997314.515, "dur": 1014.579, + "args": { + "External id": 1404980,"Record function id": 0, "Ev Idx": 13944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530997400.046, "dur": 10.149, + "args": { + "External id": 1404981,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530997438.576, "dur": 39.053, + "args": { + "External id": 1404982,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997444.812, "dur": 2.381, + "args": { + "External id": 1404983,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997452.052, "dur": 0.644, + "args": { + "External id": 1404984,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997454.312, "dur": 0.564, + "args": { + "External id": 1404985,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997456.306, "dur": 0.555, + "args": { + "External id": 1404986,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997459.640, "dur": 0.447, + "args": { + "External id": 1404987,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997461.390, "dur": 0.476, + "args": { + "External id": 1404988,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997463.638, "dur": 3.511, + "args": { + "External id": 1404989,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997468.789, "dur": 0.551, + "args": { + "External id": 1404990,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997471.072, "dur": 0.616, + "args": { + "External id": 1404991,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530997489.827, "dur": 56.585, + "args": { + "External id": 1404992,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410530997581.681, "dur": 125.459, + "args": { + "External id": 1404993,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530997593.667, "dur": 6.158, + "args": { + "External id": 1404994,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410530997605.520, "dur": 10.644, + "args": { + "External id": 1404995,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410530997610.053, "dur": 5.721, + "args": { + "External id": 1404996,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997613.965, "dur": 0.522, + "args": { + "External id": 1404997,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410530997623.060, "dur": 27.727, + "args": { + "External id": 1404998,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997625.259, "dur": 1.358, + "args": { + "External id": 1404999,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997628.403, "dur": 0.526, + "args": { + "External id": 1405000,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997630.527, "dur": 0.526, + "args": { + "External id": 1405001,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997633.577, "dur": 2.181, + "args": { + "External id": 1405002,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997637.502, "dur": 0.272, + "args": { + "External id": 1405003,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997639.298, "dur": 0.239, + "args": { + "External id": 1405004,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997641.792, "dur": 0.285, + "args": { + "External id": 1405005,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997643.508, "dur": 0.319, + "args": { + "External id": 1405006,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530997645.563, "dur": 1.285, + "args": { + "External id": 1405007,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530997664.223, "dur": 34.957, + "args": { + "External id": 1405008,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410530997761.534, "dur": 458.925, + "args": { + "External id": 1405009,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530997799.164, "dur": 415.170, + "args": { + "External id": 1405010,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13974, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410530997809.697, "dur": 397.928, + "args": { + "External id": 1405011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410530998249.296, "dur": 2.222, + "args": { + "External id": 1405012,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 13976, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338710, "tid": 2338710, + "ts": 6410530998350.295, "dur": 31017.052, + "args": { + "External id": 1405013,"Record function id": 0, "Ev Idx": 13977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998475.733, "dur": 6.926, + "args": { + "External id": 1405014,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998493.137, "dur": 1.338, + "args": { + "External id": 1405015,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998496.048, "dur": 3.624, + "args": { + "External id": 1405016,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998503.649, "dur": 0.914, + "args": { + "External id": 1405017,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998505.844, "dur": 1.159, + "args": { + "External id": 1405018,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998508.317, "dur": 1.005, + "args": { + "External id": 1405019,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998510.905, "dur": 0.819, + "args": { + "External id": 1405020,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998515.362, "dur": 1.966, + "args": { + "External id": 1405021,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998518.943, "dur": 0.871, + "args": { + "External id": 1405022,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410530998521.258, "dur": 1.018, + "args": { + "External id": 1405023,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530998542.654, "dur": 30783.513, + "args": { + "External id": 1405024,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530998558.692, "dur": 30759.424, + "args": { + "External id": 1405025,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410530998575.792, "dur": 16.517, + "args": { + "External id": 1405026,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410530998598.116, "dur": 30686.164, + "args": { + "External id": 1405027,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410530998600.609, "dur": 30683.207, + "args": { + "External id": 1405028,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410530998606.153, "dur": 5.771, + "args": { + "External id": 1405029,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410530998613.675, "dur": 30666.954, + "args": { + "External id": 1405030,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531029514.920, "dur": 31.144, + "args": { + "External id": 1405031,"Sequence number": 15108891, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13995 + } + }, + { + "ph": "s", "id": 175, "pid": 2338710, "tid": 2338710, "ts": 6410531029514.920, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410531029531.957, "dur": 8.757, + "args": { + "External id": 1405032,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531029536.020, "dur": 4.349, + "args": { + "External id": 1405033,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410531029611.618, "dur": 70.460, + "args": { + "External id": 1405034,"Record function id": 0, "Ev Idx": 13998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410531029683.478, "dur": 1144.850, + "args": { + "External id": 1405035,"Record function id": 0, "Ev Idx": 13999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531029722.003, "dur": 1092.441, + "args": { + "External id": 1405036,"Sequence number": 15108892, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 14000 + } + }, + { + "ph": "s", "id": 174, "pid": 2338710, "tid": 2338710, "ts": 6410531029722.003, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410531029788.593, "dur": 48.834, + "args": { + "External id": 1405037,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 14001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531029849.140, "dur": 101.889, + "args": { + "External id": 1405038,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 14002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531029961.651, "dur": 38.387, + "args": { + "External id": 1405039,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 14003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531030007.807, "dur": 31.919, + "args": { + "External id": 1405040,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 14004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410531030115.988, "dur": 33.059, + "args": { + "External id": 1405041,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 14005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410531030173.513, "dur": 18.585, + "args": { + "External id": 1405042,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 14006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410531030214.256, "dur": 132.538, + "args": { + "External id": 1405043,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531030265.868, "dur": 12.236, + "args": { + "External id": 1405044,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531030271.927, "dur": 5.333, + "args": { + "External id": 1405045,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531030280.815, "dur": 4.056, + "args": { + "External id": 1405046,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531030286.404, "dur": 1.413, + "args": { + "External id": 1405047,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531030290.275, "dur": 5.254, + "args": { + "External id": 1405048,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531030357.567, "dur": 72.692, + "args": { + "External id": 1405049,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 14013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410531030467.318, "dur": 32.554, + "args": { + "External id": 1405050,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 14014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531030510.204, "dur": 47.218, + "args": { + "External id": 1405051,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 14015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531030566.034, "dur": 36.733, + "args": { + "External id": 1405052,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 14016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410531030635.237, "dur": 27.010, + "args": { + "External id": 1405053,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 14017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531030669.778, "dur": 37.293, + "args": { + "External id": 1405054,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 14018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410531030726.758, "dur": 19.881, + "args": { + "External id": 1405055,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 14019 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.24)", "pid": 2338710, "tid": 2338710, + "ts": 6410531030894.155, "dur": 79.783, + "args": { + "External id": 1405056,"Record function id": 0, "Ev Idx": 14020 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410531031050.709, "dur": 102.118, + "args": { + "External id": 1405057,"Record function id": 0, "Ev Idx": 14021 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 2338710, "tid": 2338710, + "ts": 6410531031163.642, "dur": 33671.316, + "args": { + "External id": 1405058,"Record function id": 0, "Ev Idx": 14022 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 2338710, "tid": 2338710, + "ts": 6410531031173.402, "dur": 962.092, + "args": { + "External id": 1405059,"Record function id": 0, "Ev Idx": 14023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531031262.393, "dur": 10.139, + "args": { + "External id": 1405060,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410531031286.366, "dur": 40.301, + "args": { + "External id": 1405061,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 14025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031292.278, "dur": 2.605, + "args": { + "External id": 1405062,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031298.769, "dur": 0.550, + "args": { + "External id": 1405063,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031300.943, "dur": 0.622, + "args": { + "External id": 1405064,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031303.480, "dur": 0.986, + "args": { + "External id": 1405065,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031307.291, "dur": 0.928, + "args": { + "External id": 1405066,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031309.747, "dur": 0.544, + "args": { + "External id": 1405067,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031312.111, "dur": 4.627, + "args": { + "External id": 1405068,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031318.505, "dur": 0.470, + "args": { + "External id": 1405069,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031320.536, "dur": 0.583, + "args": { + "External id": 1405070,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531031338.339, "dur": 55.619, + "args": { + "External id": 1405071,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 14035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410531031443.544, "dur": 135.736, + "args": { + "External id": 1405072,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 14036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531031456.202, "dur": 5.723, + "args": { + "External id": 1405073,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410531031467.674, "dur": 11.686, + "args": { + "External id": 1405074,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 14038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531031472.665, "dur": 6.301, + "args": { + "External id": 1405075,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 14039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031476.549, "dur": 0.684, + "args": { + "External id": 1405076,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 14040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410531031486.925, "dur": 32.040, + "args": { + "External id": 1405077,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 14041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031489.345, "dur": 2.460, + "args": { + "External id": 1405078,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031493.972, "dur": 0.424, + "args": { + "External id": 1405079,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031496.403, "dur": 0.664, + "args": { + "External id": 1405080,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031500.137, "dur": 2.240, + "args": { + "External id": 1405081,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031504.157, "dur": 0.403, + "args": { + "External id": 1405082,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031506.338, "dur": 0.241, + "args": { + "External id": 1405083,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031509.808, "dur": 0.201, + "args": { + "External id": 1405084,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031511.200, "dur": 0.433, + "args": { + "External id": 1405085,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531031513.078, "dur": 2.218, + "args": { + "External id": 1405086,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531031533.160, "dur": 37.986, + "args": { + "External id": 1405087,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 14051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410531031635.729, "dur": 359.006, + "args": { + "External id": 1405088,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 14052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410531031666.781, "dur": 322.981, + "args": { + "External id": 1405089,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 14053, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410531031677.663, "dur": 306.583, + "args": { + "External id": 1405090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 14054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410531032017.088, "dur": 2.097, + "args": { + "External id": 1405091,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 14055, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 2338710, "tid": 2338710, + "ts": 6410531032158.030, "dur": 32468.306, + "args": { + "External id": 1405092,"Record function id": 0, "Ev Idx": 14056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032265.395, "dur": 7.048, + "args": { + "External id": 1405093,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 14057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032275.632, "dur": 1.115, + "args": { + "External id": 1405094,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032278.665, "dur": 3.360, + "args": { + "External id": 1405095,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 14059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032283.516, "dur": 0.967, + "args": { + "External id": 1405096,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 14060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032285.545, "dur": 0.909, + "args": { + "External id": 1405097,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 14061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032287.495, "dur": 0.951, + "args": { + "External id": 1405098,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 14062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032292.002, "dur": 0.743, + "args": { + "External id": 1405099,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032294.203, "dur": 1.889, + "args": { + "External id": 1405100,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 14064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032297.262, "dur": 0.870, + "args": { + "External id": 1405101,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 14065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531032299.288, "dur": 0.809, + "args": { + "External id": 1405102,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 14066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531032320.315, "dur": 32253.065, + "args": { + "External id": 1405103,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 14067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531032336.394, "dur": 32227.360, + "args": { + "External id": 1405104,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 14068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531032361.458, "dur": 17.727, + "args": { + "External id": 1405105,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531032382.885, "dur": 32138.299, + "args": { + "External id": 1405106,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 14070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531032385.515, "dur": 32134.827, + "args": { + "External id": 1405107,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 14071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531032391.418, "dur": 5.621, + "args": { + "External id": 1405108,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531032398.779, "dur": 32117.246, + "args": { + "External id": 1405109,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 14073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531064772.228, "dur": 35.840, + "args": { + "External id": 1405110,"Sequence number": 15108893, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 14074 + } + }, + { + "ph": "s", "id": 173, "pid": 2338710, "tid": 2338710, "ts": 6410531064772.228, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410531064791.821, "dur": 11.183, + "args": { + "External id": 1405111,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 14075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531064796.805, "dur": 5.932, + "args": { + "External id": 1405112,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410531064875.096, "dur": 67.742, + "args": { + "External id": 1405113,"Record function id": 0, "Ev Idx": 14077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410531064944.072, "dur": 1161.233, + "args": { + "External id": 1405114,"Record function id": 0, "Ev Idx": 14078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531064985.020, "dur": 1059.843, + "args": { + "External id": 1405115,"Sequence number": 15108894, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 14079 + } + }, + { + "ph": "s", "id": 172, "pid": 2338710, "tid": 2338710, "ts": 6410531064985.020, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410531065051.172, "dur": 83.773, + "args": { + "External id": 1405116,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 14080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531065152.303, "dur": 105.529, + "args": { + "External id": 1405117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 14081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531065268.759, "dur": 37.841, + "args": { + "External id": 1405118,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 14082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531065314.794, "dur": 29.636, + "args": { + "External id": 1405119,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 14083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410531065371.938, "dur": 25.743, + "args": { + "External id": 1405120,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 14084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410531065434.375, "dur": 23.385, + "args": { + "External id": 1405121,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 14085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410531065482.290, "dur": 133.175, + "args": { + "External id": 1405122,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531065533.038, "dur": 12.862, + "args": { + "External id": 1405123,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531065539.078, "dur": 5.993, + "args": { + "External id": 1405124,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531065548.509, "dur": 4.509, + "args": { + "External id": 1405125,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531065554.192, "dur": 1.501, + "args": { + "External id": 1405126,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531065557.986, "dur": 4.939, + "args": { + "External id": 1405127,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531065625.779, "dur": 54.440, + "args": { + "External id": 1405128,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 14092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410531065711.129, "dur": 32.551, + "args": { + "External id": 1405129,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 14093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531065753.032, "dur": 44.935, + "args": { + "External id": 1405130,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 14094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531065807.622, "dur": 35.179, + "args": { + "External id": 1405131,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 14095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410531065866.376, "dur": 27.435, + "args": { + "External id": 1405132,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 14096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531065901.316, "dur": 36.325, + "args": { + "External id": 1405133,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 14097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410531065955.425, "dur": 17.877, + "args": { + "External id": 1405134,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 14098 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.25)", "pid": 2338710, "tid": 2338710, + "ts": 6410531066174.123, "dur": 34.024, + "args": { + "External id": 1405135,"Record function id": 0, "Ev Idx": 14099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531066339.755, "dur": 288.702, + "args": { + "External id": 1405136,"Sequence number": 15108895, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 14100 + } + }, + { + "ph": "s", "id": 171, "pid": 2338710, "tid": 2338710, "ts": 6410531066339.755, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531066369.983, "dur": 9.004, + "args": { + "External id": 1405137,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066372.321, "dur": 6.431, + "args": { + "External id": 1405138,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531066388.161, "dur": 13.108, + "args": { + "External id": 1405139,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531066391.680, "dur": 9.049, + "args": { + "External id": 1405140,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531066411.087, "dur": 19.660, + "args": { + "External id": 1405141,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531066604.718, "dur": 7.980, + "args": { + "External id": 1405142,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066608.221, "dur": 4.240, + "args": { + "External id": 1405143,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531066655.925, "dur": 147.602, + "args": { + "External id": 1405144,"Sequence number": 15108896, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531066658.539, "dur": 14.924, + "args": { + "External id": 1405145,"Sequence number": 15108896, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14109 + } + }, + { + "ph": "s", "id": 170, "pid": 2338710, "tid": 2338710, "ts": 6410531066658.539, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531066664.068, "dur": 7.759, + "args": { + "External id": 1405146,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531066669.422, "dur": 2.055, + "args": { + "External id": 1405147,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531066675.859, "dur": 127.317, + "args": { + "External id": 1405148,"Sequence number": 15108897, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531066678.547, "dur": 4.875, + "args": { + "External id": 1405149,"Sequence number": 15108897, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066679.661, "dur": 3.637, + "args": { + "External id": 1405150,"Sequence number": 15108897, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14114 + } + }, + { + "ph": "s", "id": 169, "pid": 2338710, "tid": 2338710, "ts": 6410531066679.661, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531066687.649, "dur": 99.520, + "args": { + "External id": 1405151,"Sequence number": 15108898, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14115 + } + }, + { + "ph": "s", "id": 168, "pid": 2338710, "tid": 2338710, "ts": 6410531066687.649, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066794.075, "dur": 8.006, + "args": { + "External id": 1405152,"Sequence number": 15108899, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14116 + } + }, + { + "ph": "s", "id": 167, "pid": 2338710, "tid": 2338710, "ts": 6410531066794.075, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531066813.487, "dur": 69.051, + "args": { + "External id": 1405153,"Sequence number": 15108900, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531066814.238, "dur": 8.080, + "args": { + "External id": 1405154,"Sequence number": 15108900, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14118 + } + }, + { + "ph": "s", "id": 166, "pid": 2338710, "tid": 2338710, "ts": 6410531066814.238, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531066816.622, "dur": 4.493, + "args": { + "External id": 1405155,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531066820.118, "dur": 0.821, + "args": { + "External id": 1405156,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531066822.936, "dur": 59.353, + "args": { + "External id": 1405157,"Sequence number": 15108901, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531066824.212, "dur": 4.558, + "args": { + "External id": 1405158,"Sequence number": 15108901, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066825.085, "dur": 3.547, + "args": { + "External id": 1405159,"Sequence number": 15108901, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14123 + } + }, + { + "ph": "s", "id": 165, "pid": 2338710, "tid": 2338710, "ts": 6410531066825.085, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531066829.342, "dur": 45.870, + "args": { + "External id": 1405160,"Sequence number": 15108902, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14124 + } + }, + { + "ph": "s", "id": 164, "pid": 2338710, "tid": 2338710, "ts": 6410531066829.342, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066877.142, "dur": 4.745, + "args": { + "External id": 1405161,"Sequence number": 15108903, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14125 + } + }, + { + "ph": "s", "id": 163, "pid": 2338710, "tid": 2338710, "ts": 6410531066877.142, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531066890.282, "dur": 64.192, + "args": { + "External id": 1405162,"Sequence number": 15108904, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531066890.782, "dur": 6.026, + "args": { + "External id": 1405163,"Sequence number": 15108904, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14127 + } + }, + { + "ph": "s", "id": 162, "pid": 2338710, "tid": 2338710, "ts": 6410531066890.782, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531066892.936, "dur": 2.320, + "args": { + "External id": 1405164,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531066894.429, "dur": 0.691, + "args": { + "External id": 1405165,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531066899.845, "dur": 54.397, + "args": { + "External id": 1405166,"Sequence number": 15108905, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531066901.083, "dur": 4.746, + "args": { + "External id": 1405167,"Sequence number": 15108905, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066901.955, "dur": 3.724, + "args": { + "External id": 1405168,"Sequence number": 15108905, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14132 + } + }, + { + "ph": "s", "id": 161, "pid": 2338710, "tid": 2338710, "ts": 6410531066901.955, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531066906.374, "dur": 40.189, + "args": { + "External id": 1405169,"Sequence number": 15108906, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14133 + } + }, + { + "ph": "s", "id": 160, "pid": 2338710, "tid": 2338710, "ts": 6410531066906.374, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066948.453, "dur": 5.396, + "args": { + "External id": 1405170,"Sequence number": 15108907, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14134 + } + }, + { + "ph": "s", "id": 159, "pid": 2338710, "tid": 2338710, "ts": 6410531066948.453, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531066973.316, "dur": 3.706, + "args": { + "External id": 1405171,"Sequence number": 15108908, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066974.240, "dur": 2.668, + "args": { + "External id": 1405172,"Sequence number": 15108908, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14136 + } + }, + { + "ph": "s", "id": 158, "pid": 2338710, "tid": 2338710, "ts": 6410531066974.240, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531066984.244, "dur": 2.777, + "args": { + "External id": 1405173,"Sequence number": 15108909, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066985.087, "dur": 1.806, + "args": { + "External id": 1405174,"Sequence number": 15108909, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14138 + } + }, + { + "ph": "s", "id": 157, "pid": 2338710, "tid": 2338710, "ts": 6410531066985.087, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531066993.208, "dur": 4.919, + "args": { + "External id": 1405175,"Sequence number": 15108910, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531066994.353, "dur": 3.632, + "args": { + "External id": 1405176,"Sequence number": 15108910, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14140 + } + }, + { + "ph": "s", "id": 156, "pid": 2338710, "tid": 2338710, "ts": 6410531066994.353, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531067032.998, "dur": 244.958, + "args": { + "External id": 1405177,"Sequence number": 15108911, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14141 + } + }, + { + "ph": "s", "id": 155, "pid": 2338710, "tid": 2338710, "ts": 6410531067032.998, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531067107.838, "dur": 11.869, + "args": { + "External id": 1405178,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531067111.624, "dur": 7.270, + "args": { + "External id": 1405179,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531067294.681, "dur": 108.796, + "args": { + "External id": 1405180,"Sequence number": 15108912, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14144 + } + }, + { + "ph": "s", "id": 154, "pid": 2338710, "tid": 2338710, "ts": 6410531067294.681, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531067309.796, "dur": 7.222, + "args": { + "External id": 1405181,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 14145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531067312.428, "dur": 4.210, + "args": { + "External id": 1405182,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338710, "tid": 2338710, + "ts": 6410531067454.495, "dur": 198.676, + "args": { + "External id": 1405183,"Sequence number": 15108913, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 14147 + } + }, + { + "ph": "s", "id": 153, "pid": 2338710, "tid": 2338710, "ts": 6410531067454.495, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410531067482.839, "dur": 140.902, + "args": { + "External id": 1405184,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531067536.867, "dur": 9.341, + "args": { + "External id": 1405185,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531067539.647, "dur": 5.856, + "args": { + "External id": 1405186,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531067552.923, "dur": 4.373, + "args": { + "External id": 1405187,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531067560.360, "dur": 1.596, + "args": { + "External id": 1405188,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531067564.219, "dur": 3.344, + "args": { + "External id": 1405189,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410531067638.052, "dur": 5.343, + "args": { + "External id": 1405190,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 14154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531067659.444, "dur": 6.467, + "args": { + "External id": 1405191,"Sequence number": 15108914, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531067661.028, "dur": 4.683, + "args": { + "External id": 1405192,"Sequence number": 15108914, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14156 + } + }, + { + "ph": "s", "id": 152, "pid": 2338710, "tid": 2338710, "ts": 6410531067661.028, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531067681.950, "dur": 115.293, + "args": { + "External id": 1405193,"Sequence number": 15108915, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531067683.396, "dur": 9.225, + "args": { + "External id": 1405194,"Sequence number": 15108915, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14158 + } + }, + { + "ph": "s", "id": 151, "pid": 2338710, "tid": 2338710, "ts": 6410531067683.396, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531067686.404, "dur": 5.037, + "args": { + "External id": 1405195,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531067689.191, "dur": 1.951, + "args": { + "External id": 1405196,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531067694.034, "dur": 102.861, + "args": { + "External id": 1405197,"Sequence number": 15108916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531067698.145, "dur": 2.921, + "args": { + "External id": 1405198,"Sequence number": 15108916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531067698.683, "dur": 2.260, + "args": { + "External id": 1405199,"Sequence number": 15108916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14163 + } + }, + { + "ph": "s", "id": 150, "pid": 2338710, "tid": 2338710, "ts": 6410531067698.683, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531067702.027, "dur": 88.524, + "args": { + "External id": 1405200,"Sequence number": 15108917, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14164 + } + }, + { + "ph": "s", "id": 149, "pid": 2338710, "tid": 2338710, "ts": 6410531067702.027, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531067793.265, "dur": 3.035, + "args": { + "External id": 1405201,"Sequence number": 15108918, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14165 + } + }, + { + "ph": "s", "id": 148, "pid": 2338710, "tid": 2338710, "ts": 6410531067793.265, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531067830.149, "dur": 215.229, + "args": { + "External id": 1405202,"Sequence number": 15108919, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 14166 + } + }, + { + "ph": "s", "id": 147, "pid": 2338710, "tid": 2338710, "ts": 6410531067830.149, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531067851.309, "dur": 2.495, + "args": { + "External id": 1405203,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531067851.975, "dur": 1.692, + "args": { + "External id": 1405204,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338710, "tid": 2338710, + "ts": 6410531067858.557, "dur": 6.641, + "args": { + "External id": 1405205,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 14169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531067859.622, "dur": 5.459, + "args": { + "External id": 1405206,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531067862.511, "dur": 2.466, + "args": { + "External id": 1405207,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531067872.934, "dur": 6.044, + "args": { + "External id": 1405208,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531067874.925, "dur": 3.692, + "args": { + "External id": 1405209,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531067885.005, "dur": 2.733, + "args": { + "External id": 1405210,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531067893.171, "dur": 3.013, + "args": { + "External id": 1405211,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068022.643, "dur": 3.338, + "args": { + "External id": 1405212,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068023.500, "dur": 2.178, + "args": { + "External id": 1405213,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068030.722, "dur": 1.889, + "args": { + "External id": 1405214,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068031.574, "dur": 0.929, + "args": { + "External id": 1405215,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531068116.576, "dur": 114.960, + "args": { + "External id": 1405216,"Sequence number": 15108920, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531068117.761, "dur": 9.596, + "args": { + "External id": 1405217,"Sequence number": 15108920, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14181 + } + }, + { + "ph": "s", "id": 146, "pid": 2338710, "tid": 2338710, "ts": 6410531068117.761, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531068120.896, "dur": 4.825, + "args": { + "External id": 1405218,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531068123.491, "dur": 1.781, + "args": { + "External id": 1405219,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531068130.720, "dur": 100.507, + "args": { + "External id": 1405220,"Sequence number": 15108921, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068132.685, "dur": 4.233, + "args": { + "External id": 1405221,"Sequence number": 15108921, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068133.770, "dur": 3.025, + "args": { + "External id": 1405222,"Sequence number": 15108921, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14186 + } + }, + { + "ph": "s", "id": 145, "pid": 2338710, "tid": 2338710, "ts": 6410531068133.770, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531068137.659, "dur": 81.672, + "args": { + "External id": 1405223,"Sequence number": 15108922, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14187 + } + }, + { + "ph": "s", "id": 144, "pid": 2338710, "tid": 2338710, "ts": 6410531068137.659, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068222.032, "dur": 8.553, + "args": { + "External id": 1405224,"Sequence number": 15108923, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14188 + } + }, + { + "ph": "s", "id": 143, "pid": 2338710, "tid": 2338710, "ts": 6410531068222.032, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531068241.162, "dur": 69.974, + "args": { + "External id": 1405225,"Sequence number": 15108924, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531068241.925, "dur": 5.969, + "args": { + "External id": 1405226,"Sequence number": 15108924, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14190 + } + }, + { + "ph": "s", "id": 142, "pid": 2338710, "tid": 2338710, "ts": 6410531068241.925, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531068243.472, "dur": 2.958, + "args": { + "External id": 1405227,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531068245.567, "dur": 0.722, + "args": { + "External id": 1405228,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531068248.637, "dur": 62.264, + "args": { + "External id": 1405229,"Sequence number": 15108925, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068251.545, "dur": 5.003, + "args": { + "External id": 1405230,"Sequence number": 15108925, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068252.603, "dur": 3.737, + "args": { + "External id": 1405231,"Sequence number": 15108925, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14195 + } + }, + { + "ph": "s", "id": 141, "pid": 2338710, "tid": 2338710, "ts": 6410531068252.603, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531068257.234, "dur": 49.891, + "args": { + "External id": 1405232,"Sequence number": 15108926, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14196 + } + }, + { + "ph": "s", "id": 140, "pid": 2338710, "tid": 2338710, "ts": 6410531068257.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068308.948, "dur": 1.615, + "args": { + "External id": 1405233,"Sequence number": 15108927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14197 + } + }, + { + "ph": "s", "id": 139, "pid": 2338710, "tid": 2338710, "ts": 6410531068308.948, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531068337.038, "dur": 190.105, + "args": { + "External id": 1405234,"Sequence number": 15108928, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14198 + } + }, + { + "ph": "s", "id": 138, "pid": 2338710, "tid": 2338710, "ts": 6410531068337.038, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531068381.190, "dur": 4.182, + "args": { + "External id": 1405235,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531068435.132, "dur": 76.200, + "args": { + "External id": 1405236,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531068435.992, "dur": 8.807, + "args": { + "External id": 1405237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 14201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531068437.780, "dur": 5.677, + "args": { + "External id": 1405238,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 14202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531068441.945, "dur": 1.178, + "args": { + "External id": 1405239,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 14203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531068447.519, "dur": 63.386, + "args": { + "External id": 1405240,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 14204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068448.990, "dur": 2.118, + "args": { + "External id": 1405241,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068449.774, "dur": 1.211, + "args": { + "External id": 1405242,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531068451.491, "dur": 55.170, + "args": { + "External id": 1405243,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 14207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068508.898, "dur": 1.356, + "args": { + "External id": 1405244,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410531068538.201, "dur": 27.224, + "args": { + "External id": 1405245,"Sequence number": 15108929, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 14209 + } + }, + { + "ph": "s", "id": 137, "pid": 2338710, "tid": 2338710, "ts": 6410531068538.201, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531068603.864, "dur": 191.955, + "args": { + "External id": 1405246,"Sequence number": 15108930, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 14210 + } + }, + { + "ph": "s", "id": 136, "pid": 2338710, "tid": 2338710, "ts": 6410531068603.864, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068625.104, "dur": 3.631, + "args": { + "External id": 1405247,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068626.294, "dur": 2.224, + "args": { + "External id": 1405248,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531068637.466, "dur": 7.355, + "args": { + "External id": 1405249,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531068639.992, "dur": 4.373, + "args": { + "External id": 1405250,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531068650.912, "dur": 3.809, + "args": { + "External id": 1405251,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068778.172, "dur": 3.101, + "args": { + "External id": 1405252,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068779.093, "dur": 2.015, + "args": { + "External id": 1405253,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531068813.497, "dur": 85.468, + "args": { + "External id": 1405254,"Sequence number": 15108931, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531068814.202, "dur": 6.908, + "args": { + "External id": 1405255,"Sequence number": 15108931, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14219 + } + }, + { + "ph": "s", "id": 135, "pid": 2338710, "tid": 2338710, "ts": 6410531068814.202, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531068816.467, "dur": 3.314, + "args": { + "External id": 1405256,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531068818.404, "dur": 1.221, + "args": { + "External id": 1405257,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531068822.001, "dur": 76.589, + "args": { + "External id": 1405258,"Sequence number": 15108932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068825.457, "dur": 5.442, + "args": { + "External id": 1405259,"Sequence number": 15108932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068826.097, "dur": 4.640, + "args": { + "External id": 1405260,"Sequence number": 15108932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14224 + } + }, + { + "ph": "s", "id": 134, "pid": 2338710, "tid": 2338710, "ts": 6410531068826.097, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531068831.483, "dur": 59.950, + "args": { + "External id": 1405261,"Sequence number": 15108933, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14225 + } + }, + { + "ph": "s", "id": 133, "pid": 2338710, "tid": 2338710, "ts": 6410531068831.483, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068893.563, "dur": 4.385, + "args": { + "External id": 1405262,"Sequence number": 15108934, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14226 + } + }, + { + "ph": "s", "id": 132, "pid": 2338710, "tid": 2338710, "ts": 6410531068893.563, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531068906.699, "dur": 70.640, + "args": { + "External id": 1405263,"Sequence number": 15108935, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531068909.661, "dur": 8.591, + "args": { + "External id": 1405264,"Sequence number": 15108935, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14228 + } + }, + { + "ph": "s", "id": 131, "pid": 2338710, "tid": 2338710, "ts": 6410531068909.661, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531068914.495, "dur": 2.740, + "args": { + "External id": 1405265,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531068916.469, "dur": 0.583, + "args": { + "External id": 1405266,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531068918.739, "dur": 58.310, + "args": { + "External id": 1405267,"Sequence number": 15108936, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068919.530, "dur": 5.447, + "args": { + "External id": 1405268,"Sequence number": 15108936, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068922.622, "dur": 2.211, + "args": { + "External id": 1405269,"Sequence number": 15108936, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14233 + } + }, + { + "ph": "s", "id": 130, "pid": 2338710, "tid": 2338710, "ts": 6410531068922.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531068925.567, "dur": 44.270, + "args": { + "External id": 1405270,"Sequence number": 15108937, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14234 + } + }, + { + "ph": "s", "id": 129, "pid": 2338710, "tid": 2338710, "ts": 6410531068925.567, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068971.828, "dur": 4.615, + "args": { + "External id": 1405271,"Sequence number": 15108938, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14235 + } + }, + { + "ph": "s", "id": 128, "pid": 2338710, "tid": 2338710, "ts": 6410531068971.828, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531068984.457, "dur": 60.666, + "args": { + "External id": 1405272,"Sequence number": 15108939, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531068985.192, "dur": 7.982, + "args": { + "External id": 1405273,"Sequence number": 15108939, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14237 + } + }, + { + "ph": "s", "id": 127, "pid": 2338710, "tid": 2338710, "ts": 6410531068985.192, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531068989.252, "dur": 2.460, + "args": { + "External id": 1405274,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531068991.067, "dur": 0.499, + "args": { + "External id": 1405275,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531068993.626, "dur": 51.274, + "args": { + "External id": 1405276,"Sequence number": 15108940, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531068994.550, "dur": 7.700, + "args": { + "External id": 1405277,"Sequence number": 15108940, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531068995.748, "dur": 6.359, + "args": { + "External id": 1405278,"Sequence number": 15108940, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14242 + } + }, + { + "ph": "s", "id": 126, "pid": 2338710, "tid": 2338710, "ts": 6410531068995.748, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531069002.774, "dur": 38.066, + "args": { + "External id": 1405279,"Sequence number": 15108941, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14243 + } + }, + { + "ph": "s", "id": 125, "pid": 2338710, "tid": 2338710, "ts": 6410531069002.774, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069042.579, "dur": 1.993, + "args": { + "External id": 1405280,"Sequence number": 15108942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14244 + } + }, + { + "ph": "s", "id": 124, "pid": 2338710, "tid": 2338710, "ts": 6410531069042.579, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531069110.192, "dur": 5.342, + "args": { + "External id": 1405281,"Sequence number": 15108943, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069111.378, "dur": 3.914, + "args": { + "External id": 1405282,"Sequence number": 15108943, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14246 + } + }, + { + "ph": "s", "id": 123, "pid": 2338710, "tid": 2338710, "ts": 6410531069111.378, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531069127.072, "dur": 4.886, + "args": { + "External id": 1405283,"Sequence number": 15108944, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069127.757, "dur": 4.055, + "args": { + "External id": 1405284,"Sequence number": 15108944, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14248 + } + }, + { + "ph": "s", "id": 122, "pid": 2338710, "tid": 2338710, "ts": 6410531069127.757, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531069135.895, "dur": 2.682, + "args": { + "External id": 1405285,"Sequence number": 15108945, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069136.807, "dur": 1.649, + "args": { + "External id": 1405286,"Sequence number": 15108945, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14250 + } + }, + { + "ph": "s", "id": 121, "pid": 2338710, "tid": 2338710, "ts": 6410531069136.807, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531069169.005, "dur": 158.729, + "args": { + "External id": 1405287,"Sequence number": 15108946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14251 + } + }, + { + "ph": "s", "id": 120, "pid": 2338710, "tid": 2338710, "ts": 6410531069169.005, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531069188.956, "dur": 10.143, + "args": { + "External id": 1405288,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531069192.332, "dur": 6.301, + "args": { + "External id": 1405289,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531069340.018, "dur": 124.943, + "args": { + "External id": 1405290,"Sequence number": 15108947, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14254 + } + }, + { + "ph": "s", "id": 119, "pid": 2338710, "tid": 2338710, "ts": 6410531069340.018, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531069353.507, "dur": 6.936, + "args": { + "External id": 1405291,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 14255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531069356.051, "dur": 3.981, + "args": { + "External id": 1405292,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338710, "tid": 2338710, + "ts": 6410531069497.819, "dur": 180.049, + "args": { + "External id": 1405293,"Sequence number": 15108948, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 14257 + } + }, + { + "ph": "s", "id": 118, "pid": 2338710, "tid": 2338710, "ts": 6410531069497.819, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410531069526.439, "dur": 124.738, + "args": { + "External id": 1405294,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531069572.217, "dur": 11.141, + "args": { + "External id": 1405295,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531069576.119, "dur": 6.793, + "args": { + "External id": 1405296,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531069586.367, "dur": 3.728, + "args": { + "External id": 1405297,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531069591.251, "dur": 1.359, + "args": { + "External id": 1405298,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531069595.037, "dur": 2.922, + "args": { + "External id": 1405299,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410531069662.219, "dur": 4.748, + "args": { + "External id": 1405300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 14264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531069682.882, "dur": 5.754, + "args": { + "External id": 1405301,"Sequence number": 15108949, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069684.281, "dur": 4.224, + "args": { + "External id": 1405302,"Sequence number": 15108949, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14266 + } + }, + { + "ph": "s", "id": 117, "pid": 2338710, "tid": 2338710, "ts": 6410531069684.281, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531069700.972, "dur": 117.720, + "args": { + "External id": 1405303,"Sequence number": 15108950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531069702.398, "dur": 8.700, + "args": { + "External id": 1405304,"Sequence number": 15108950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14268 + } + }, + { + "ph": "s", "id": 116, "pid": 2338710, "tid": 2338710, "ts": 6410531069702.398, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531069704.680, "dur": 5.146, + "args": { + "External id": 1405305,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531069707.526, "dur": 1.983, + "args": { + "External id": 1405306,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531069714.683, "dur": 103.686, + "args": { + "External id": 1405307,"Sequence number": 15108951, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531069716.490, "dur": 3.136, + "args": { + "External id": 1405308,"Sequence number": 15108951, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069717.183, "dur": 2.316, + "args": { + "External id": 1405309,"Sequence number": 15108951, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14273 + } + }, + { + "ph": "s", "id": 115, "pid": 2338710, "tid": 2338710, "ts": 6410531069717.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531069720.461, "dur": 87.887, + "args": { + "External id": 1405310,"Sequence number": 15108952, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14274 + } + }, + { + "ph": "s", "id": 114, "pid": 2338710, "tid": 2338710, "ts": 6410531069720.461, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069811.252, "dur": 6.292, + "args": { + "External id": 1405311,"Sequence number": 15108953, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14275 + } + }, + { + "ph": "s", "id": 113, "pid": 2338710, "tid": 2338710, "ts": 6410531069811.252, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531069861.504, "dur": 271.459, + "args": { + "External id": 1405312,"Sequence number": 15108954, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 14276 + } + }, + { + "ph": "s", "id": 112, "pid": 2338710, "tid": 2338710, "ts": 6410531069861.504, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531069880.376, "dur": 4.865, + "args": { + "External id": 1405313,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069881.481, "dur": 3.592, + "args": { + "External id": 1405314,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338710, "tid": 2338710, + "ts": 6410531069889.070, "dur": 5.612, + "args": { + "External id": 1405315,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 14279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531069892.449, "dur": 2.092, + "args": { + "External id": 1405316,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531069893.198, "dur": 1.231, + "args": { + "External id": 1405317,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531069902.297, "dur": 6.710, + "args": { + "External id": 1405318,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531069904.617, "dur": 4.111, + "args": { + "External id": 1405319,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531069915.391, "dur": 2.450, + "args": { + "External id": 1405320,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531069921.110, "dur": 3.918, + "args": { + "External id": 1405321,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531070104.455, "dur": 6.567, + "args": { + "External id": 1405322,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070106.850, "dur": 3.747, + "args": { + "External id": 1405323,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531070115.169, "dur": 2.199, + "args": { + "External id": 1405324,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070116.100, "dur": 1.148, + "args": { + "External id": 1405325,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531070153.329, "dur": 113.617, + "args": { + "External id": 1405326,"Sequence number": 15108955, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531070154.418, "dur": 11.024, + "args": { + "External id": 1405327,"Sequence number": 15108955, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14291 + } + }, + { + "ph": "s", "id": 111, "pid": 2338710, "tid": 2338710, "ts": 6410531070154.418, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531070157.566, "dur": 6.556, + "args": { + "External id": 1405328,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531070162.015, "dur": 1.842, + "args": { + "External id": 1405329,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531070166.498, "dur": 99.988, + "args": { + "External id": 1405330,"Sequence number": 15108956, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531070167.997, "dur": 5.395, + "args": { + "External id": 1405331,"Sequence number": 15108956, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070168.540, "dur": 4.736, + "args": { + "External id": 1405332,"Sequence number": 15108956, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14296 + } + }, + { + "ph": "s", "id": 110, "pid": 2338710, "tid": 2338710, "ts": 6410531070168.540, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531070176.548, "dur": 84.043, + "args": { + "External id": 1405333,"Sequence number": 15108957, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14297 + } + }, + { + "ph": "s", "id": 109, "pid": 2338710, "tid": 2338710, "ts": 6410531070176.548, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070262.903, "dur": 3.055, + "args": { + "External id": 1405334,"Sequence number": 15108958, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14298 + } + }, + { + "ph": "s", "id": 108, "pid": 2338710, "tid": 2338710, "ts": 6410531070262.903, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531070275.499, "dur": 78.797, + "args": { + "External id": 1405335,"Sequence number": 15108959, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531070276.227, "dur": 13.988, + "args": { + "External id": 1405336,"Sequence number": 15108959, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14300 + } + }, + { + "ph": "s", "id": 107, "pid": 2338710, "tid": 2338710, "ts": 6410531070276.227, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531070283.650, "dur": 5.384, + "args": { + "External id": 1405337,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531070288.126, "dur": 0.763, + "args": { + "External id": 1405338,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531070290.723, "dur": 63.333, + "args": { + "External id": 1405339,"Sequence number": 15108960, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531070291.583, "dur": 5.354, + "args": { + "External id": 1405340,"Sequence number": 15108960, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070292.162, "dur": 4.634, + "args": { + "External id": 1405341,"Sequence number": 15108960, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14305 + } + }, + { + "ph": "s", "id": 106, "pid": 2338710, "tid": 2338710, "ts": 6410531070292.162, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531070297.394, "dur": 49.537, + "args": { + "External id": 1405342,"Sequence number": 15108961, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14306 + } + }, + { + "ph": "s", "id": 105, "pid": 2338710, "tid": 2338710, "ts": 6410531070297.394, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070348.601, "dur": 5.171, + "args": { + "External id": 1405343,"Sequence number": 15108962, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14307 + } + }, + { + "ph": "s", "id": 104, "pid": 2338710, "tid": 2338710, "ts": 6410531070348.601, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531070376.676, "dur": 186.584, + "args": { + "External id": 1405344,"Sequence number": 15108963, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14308 + } + }, + { + "ph": "s", "id": 103, "pid": 2338710, "tid": 2338710, "ts": 6410531070376.676, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531070436.272, "dur": 5.907, + "args": { + "External id": 1405345,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531070482.037, "dur": 66.317, + "args": { + "External id": 1405346,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531070483.116, "dur": 6.394, + "args": { + "External id": 1405347,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 14311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531070484.522, "dur": 3.851, + "args": { + "External id": 1405348,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 14312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531070486.533, "dur": 1.576, + "args": { + "External id": 1405349,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 14313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531070490.399, "dur": 57.597, + "args": { + "External id": 1405350,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 14314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531070491.870, "dur": 2.640, + "args": { + "External id": 1405351,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070492.897, "dur": 1.520, + "args": { + "External id": 1405352,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531070495.056, "dur": 48.798, + "args": { + "External id": 1405353,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 14317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070546.130, "dur": 1.231, + "args": { + "External id": 1405354,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410531070572.237, "dur": 26.699, + "args": { + "External id": 1405355,"Sequence number": 15108964, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 14319 + } + }, + { + "ph": "s", "id": 102, "pid": 2338710, "tid": 2338710, "ts": 6410531070572.237, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531070639.019, "dur": 214.660, + "args": { + "External id": 1405356,"Sequence number": 15108965, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 14320 + } + }, + { + "ph": "s", "id": 101, "pid": 2338710, "tid": 2338710, "ts": 6410531070639.019, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531070658.386, "dur": 3.188, + "args": { + "External id": 1405357,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070659.480, "dur": 1.952, + "args": { + "External id": 1405358,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531070670.070, "dur": 7.118, + "args": { + "External id": 1405359,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531070673.132, "dur": 3.728, + "args": { + "External id": 1405360,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531070683.650, "dur": 5.411, + "args": { + "External id": 1405361,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531070830.027, "dur": 4.016, + "args": { + "External id": 1405362,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070831.390, "dur": 2.353, + "args": { + "External id": 1405363,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531070883.346, "dur": 141.844, + "args": { + "External id": 1405364,"Sequence number": 15108966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531070884.958, "dur": 14.807, + "args": { + "External id": 1405365,"Sequence number": 15108966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14329 + } + }, + { + "ph": "s", "id": 100, "pid": 2338710, "tid": 2338710, "ts": 6410531070884.958, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531070890.596, "dur": 5.963, + "args": { + "External id": 1405366,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531070894.330, "dur": 1.687, + "args": { + "External id": 1405367,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531070903.717, "dur": 120.960, + "args": { + "External id": 1405368,"Sequence number": 15108967, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531070906.044, "dur": 6.900, + "args": { + "External id": 1405369,"Sequence number": 15108967, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531070907.090, "dur": 5.675, + "args": { + "External id": 1405370,"Sequence number": 15108967, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14334 + } + }, + { + "ph": "s", "id": 99, "pid": 2338710, "tid": 2338710, "ts": 6410531070907.090, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531070914.857, "dur": 101.194, + "args": { + "External id": 1405371,"Sequence number": 15108968, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14335 + } + }, + { + "ph": "s", "id": 98, "pid": 2338710, "tid": 2338710, "ts": 6410531070914.857, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071019.217, "dur": 4.733, + "args": { + "External id": 1405372,"Sequence number": 15108969, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14336 + } + }, + { + "ph": "s", "id": 97, "pid": 2338710, "tid": 2338710, "ts": 6410531071019.217, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531071037.676, "dur": 127.642, + "args": { + "External id": 1405373,"Sequence number": 15108970, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531071038.424, "dur": 6.620, + "args": { + "External id": 1405374,"Sequence number": 15108970, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14338 + } + }, + { + "ph": "s", "id": 96, "pid": 2338710, "tid": 2338710, "ts": 6410531071038.424, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531071039.892, "dur": 3.622, + "args": { + "External id": 1405375,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531071042.087, "dur": 1.157, + "args": { + "External id": 1405376,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531071045.978, "dur": 119.039, + "args": { + "External id": 1405377,"Sequence number": 15108971, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531071049.429, "dur": 3.120, + "args": { + "External id": 1405378,"Sequence number": 15108971, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071050.144, "dur": 2.271, + "args": { + "External id": 1405379,"Sequence number": 15108971, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14343 + } + }, + { + "ph": "s", "id": 95, "pid": 2338710, "tid": 2338710, "ts": 6410531071050.144, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531071053.302, "dur": 104.942, + "args": { + "External id": 1405380,"Sequence number": 15108972, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14344 + } + }, + { + "ph": "s", "id": 94, "pid": 2338710, "tid": 2338710, "ts": 6410531071053.302, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071161.601, "dur": 2.821, + "args": { + "External id": 1405381,"Sequence number": 15108973, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14345 + } + }, + { + "ph": "s", "id": 93, "pid": 2338710, "tid": 2338710, "ts": 6410531071161.601, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531071175.175, "dur": 68.705, + "args": { + "External id": 1405382,"Sequence number": 15108974, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531071177.871, "dur": 8.548, + "args": { + "External id": 1405383,"Sequence number": 15108974, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14347 + } + }, + { + "ph": "s", "id": 92, "pid": 2338710, "tid": 2338710, "ts": 6410531071177.871, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531071180.334, "dur": 4.767, + "args": { + "External id": 1405384,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531071182.161, "dur": 2.743, + "args": { + "External id": 1405385,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531071187.317, "dur": 56.276, + "args": { + "External id": 1405386,"Sequence number": 15108975, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531071188.508, "dur": 6.345, + "args": { + "External id": 1405387,"Sequence number": 15108975, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071191.307, "dur": 3.428, + "args": { + "External id": 1405388,"Sequence number": 15108975, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14352 + } + }, + { + "ph": "s", "id": 91, "pid": 2338710, "tid": 2338710, "ts": 6410531071191.307, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531071195.391, "dur": 40.211, + "args": { + "External id": 1405389,"Sequence number": 15108976, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14353 + } + }, + { + "ph": "s", "id": 90, "pid": 2338710, "tid": 2338710, "ts": 6410531071195.391, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071237.751, "dur": 5.431, + "args": { + "External id": 1405390,"Sequence number": 15108977, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14354 + } + }, + { + "ph": "s", "id": 89, "pid": 2338710, "tid": 2338710, "ts": 6410531071237.751, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531071262.966, "dur": 6.655, + "args": { + "External id": 1405391,"Sequence number": 15108978, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071266.595, "dur": 2.902, + "args": { + "External id": 1405392,"Sequence number": 15108978, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14356 + } + }, + { + "ph": "s", "id": 88, "pid": 2338710, "tid": 2338710, "ts": 6410531071266.595, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531071276.780, "dur": 2.936, + "args": { + "External id": 1405393,"Sequence number": 15108979, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071277.995, "dur": 1.607, + "args": { + "External id": 1405394,"Sequence number": 15108979, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14358 + } + }, + { + "ph": "s", "id": 87, "pid": 2338710, "tid": 2338710, "ts": 6410531071277.995, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531071283.906, "dur": 4.788, + "args": { + "External id": 1405395,"Sequence number": 15108980, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071284.844, "dur": 3.732, + "args": { + "External id": 1405396,"Sequence number": 15108980, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14360 + } + }, + { + "ph": "s", "id": 86, "pid": 2338710, "tid": 2338710, "ts": 6410531071284.844, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531071325.651, "dur": 190.429, + "args": { + "External id": 1405397,"Sequence number": 15108981, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14361 + } + }, + { + "ph": "s", "id": 85, "pid": 2338710, "tid": 2338710, "ts": 6410531071325.651, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531071349.364, "dur": 11.215, + "args": { + "External id": 1405398,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531071352.865, "dur": 6.988, + "args": { + "External id": 1405399,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531071531.932, "dur": 111.776, + "args": { + "External id": 1405400,"Sequence number": 15108982, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14364 + } + }, + { + "ph": "s", "id": 84, "pid": 2338710, "tid": 2338710, "ts": 6410531071531.932, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531071546.842, "dur": 8.163, + "args": { + "External id": 1405401,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 14365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531071549.485, "dur": 5.113, + "args": { + "External id": 1405402,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338710, "tid": 2338710, + "ts": 6410531071674.026, "dur": 174.386, + "args": { + "External id": 1405403,"Sequence number": 15108983, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 14367 + } + }, + { + "ph": "s", "id": 83, "pid": 2338710, "tid": 2338710, "ts": 6410531071674.026, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410531071698.844, "dur": 124.882, + "args": { + "External id": 1405404,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531071746.728, "dur": 7.448, + "args": { + "External id": 1405405,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531071749.162, "dur": 4.476, + "args": { + "External id": 1405406,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531071756.618, "dur": 5.160, + "args": { + "External id": 1405407,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531071762.968, "dur": 1.156, + "args": { + "External id": 1405408,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531071768.558, "dur": 3.045, + "args": { + "External id": 1405409,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410531071834.961, "dur": 4.636, + "args": { + "External id": 1405410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 14374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531071854.148, "dur": 5.357, + "args": { + "External id": 1405411,"Sequence number": 15108984, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071855.436, "dur": 3.943, + "args": { + "External id": 1405412,"Sequence number": 15108984, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14376 + } + }, + { + "ph": "s", "id": 82, "pid": 2338710, "tid": 2338710, "ts": 6410531071855.436, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531071871.471, "dur": 121.426, + "args": { + "External id": 1405413,"Sequence number": 15108985, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531071872.879, "dur": 13.593, + "args": { + "External id": 1405414,"Sequence number": 15108985, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14378 + } + }, + { + "ph": "s", "id": 81, "pid": 2338710, "tid": 2338710, "ts": 6410531071872.879, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531071878.762, "dur": 6.599, + "args": { + "External id": 1405415,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531071883.299, "dur": 1.765, + "args": { + "External id": 1405416,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531071887.925, "dur": 104.640, + "args": { + "External id": 1405417,"Sequence number": 15108986, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531071889.842, "dur": 4.604, + "args": { + "External id": 1405418,"Sequence number": 15108986, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071890.763, "dur": 3.525, + "args": { + "External id": 1405419,"Sequence number": 15108986, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14383 + } + }, + { + "ph": "s", "id": 80, "pid": 2338710, "tid": 2338710, "ts": 6410531071890.763, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531071895.308, "dur": 89.193, + "args": { + "External id": 1405420,"Sequence number": 15108987, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14384 + } + }, + { + "ph": "s", "id": 79, "pid": 2338710, "tid": 2338710, "ts": 6410531071895.308, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531071987.110, "dur": 4.732, + "args": { + "External id": 1405421,"Sequence number": 15108988, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14385 + } + }, + { + "ph": "s", "id": 78, "pid": 2338710, "tid": 2338710, "ts": 6410531071987.110, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531072027.728, "dur": 297.791, + "args": { + "External id": 1405422,"Sequence number": 15108989, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 14386 + } + }, + { + "ph": "s", "id": 77, "pid": 2338710, "tid": 2338710, "ts": 6410531072027.728, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531072046.207, "dur": 2.968, + "args": { + "External id": 1405423,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072047.216, "dur": 1.568, + "args": { + "External id": 1405424,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338710, "tid": 2338710, + "ts": 6410531072053.012, "dur": 59.200, + "args": { + "External id": 1405425,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 14389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531072108.661, "dur": 3.403, + "args": { + "External id": 1405426,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072109.999, "dur": 1.740, + "args": { + "External id": 1405427,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531072121.337, "dur": 19.405, + "args": { + "External id": 1405428,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531072131.488, "dur": 8.698, + "args": { + "External id": 1405429,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531072147.894, "dur": 4.496, + "args": { + "External id": 1405430,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531072158.039, "dur": 5.021, + "args": { + "External id": 1405431,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531072304.206, "dur": 3.287, + "args": { + "External id": 1405432,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072305.127, "dur": 2.139, + "args": { + "External id": 1405433,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531072310.125, "dur": 1.926, + "args": { + "External id": 1405434,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072310.824, "dur": 1.110, + "args": { + "External id": 1405435,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531072345.025, "dur": 156.653, + "args": { + "External id": 1405436,"Sequence number": 15108990, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531072346.200, "dur": 13.331, + "args": { + "External id": 1405437,"Sequence number": 15108990, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14401 + } + }, + { + "ph": "s", "id": 76, "pid": 2338710, "tid": 2338710, "ts": 6410531072346.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531072351.690, "dur": 6.507, + "args": { + "External id": 1405438,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531072353.926, "dur": 3.968, + "args": { + "External id": 1405439,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531072360.486, "dur": 140.880, + "args": { + "External id": 1405440,"Sequence number": 15108991, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531072381.351, "dur": 9.482, + "args": { + "External id": 1405441,"Sequence number": 15108991, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072386.554, "dur": 4.146, + "args": { + "External id": 1405442,"Sequence number": 15108991, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14406 + } + }, + { + "ph": "s", "id": 75, "pid": 2338710, "tid": 2338710, "ts": 6410531072386.554, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531072391.620, "dur": 101.560, + "args": { + "External id": 1405443,"Sequence number": 15108992, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14407 + } + }, + { + "ph": "s", "id": 74, "pid": 2338710, "tid": 2338710, "ts": 6410531072391.620, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072496.788, "dur": 3.713, + "args": { + "External id": 1405444,"Sequence number": 15108993, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14408 + } + }, + { + "ph": "s", "id": 73, "pid": 2338710, "tid": 2338710, "ts": 6410531072496.788, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531072512.851, "dur": 77.522, + "args": { + "External id": 1405445,"Sequence number": 15108994, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531072513.415, "dur": 9.996, + "args": { + "External id": 1405446,"Sequence number": 15108994, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14410 + } + }, + { + "ph": "s", "id": 72, "pid": 2338710, "tid": 2338710, "ts": 6410531072513.415, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531072515.731, "dur": 6.338, + "args": { + "External id": 1405447,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531072519.307, "dur": 2.561, + "args": { + "External id": 1405448,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531072524.164, "dur": 65.936, + "args": { + "External id": 1405449,"Sequence number": 15108995, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531072525.345, "dur": 5.794, + "args": { + "External id": 1405450,"Sequence number": 15108995, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072526.101, "dur": 4.899, + "args": { + "External id": 1405451,"Sequence number": 15108995, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14415 + } + }, + { + "ph": "s", "id": 71, "pid": 2338710, "tid": 2338710, "ts": 6410531072526.101, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531072533.973, "dur": 49.530, + "args": { + "External id": 1405452,"Sequence number": 15108996, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14416 + } + }, + { + "ph": "s", "id": 70, "pid": 2338710, "tid": 2338710, "ts": 6410531072533.973, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072585.300, "dur": 4.320, + "args": { + "External id": 1405453,"Sequence number": 15108997, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14417 + } + }, + { + "ph": "s", "id": 69, "pid": 2338710, "tid": 2338710, "ts": 6410531072585.300, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531072615.473, "dur": 169.680, + "args": { + "External id": 1405454,"Sequence number": 15108998, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14418 + } + }, + { + "ph": "s", "id": 68, "pid": 2338710, "tid": 2338710, "ts": 6410531072615.473, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531072655.646, "dur": 4.115, + "args": { + "External id": 1405455,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531072696.528, "dur": 74.956, + "args": { + "External id": 1405456,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531072697.387, "dur": 5.101, + "args": { + "External id": 1405457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 14421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531072698.504, "dur": 3.114, + "args": { + "External id": 1405458,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 14422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531072700.363, "dur": 1.037, + "args": { + "External id": 1405459,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 14423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531072703.234, "dur": 67.862, + "args": { + "External id": 1405460,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 14424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531072704.334, "dur": 2.301, + "args": { + "External id": 1405461,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072705.639, "dur": 0.902, + "args": { + "External id": 1405462,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531072709.487, "dur": 56.329, + "args": { + "External id": 1405463,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 14427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072767.667, "dur": 2.827, + "args": { + "External id": 1405464,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410531072794.111, "dur": 25.907, + "args": { + "External id": 1405465,"Sequence number": 15108999, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 14429 + } + }, + { + "ph": "s", "id": 67, "pid": 2338710, "tid": 2338710, "ts": 6410531072794.111, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531072856.062, "dur": 192.766, + "args": { + "External id": 1405466,"Sequence number": 15109000, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 14430 + } + }, + { + "ph": "s", "id": 66, "pid": 2338710, "tid": 2338710, "ts": 6410531072856.062, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531072875.898, "dur": 2.998, + "args": { + "External id": 1405467,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531072876.797, "dur": 1.873, + "args": { + "External id": 1405468,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531072886.528, "dur": 8.960, + "args": { + "External id": 1405469,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531072890.871, "dur": 4.186, + "args": { + "External id": 1405470,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531072901.565, "dur": 3.446, + "args": { + "External id": 1405471,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073033.927, "dur": 3.486, + "args": { + "External id": 1405472,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073035.224, "dur": 1.944, + "args": { + "External id": 1405473,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531073108.551, "dur": 104.262, + "args": { + "External id": 1405474,"Sequence number": 15109001, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531073109.795, "dur": 11.622, + "args": { + "External id": 1405475,"Sequence number": 15109001, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14439 + } + }, + { + "ph": "s", "id": 65, "pid": 2338710, "tid": 2338710, "ts": 6410531073109.795, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531073112.800, "dur": 6.990, + "args": { + "External id": 1405476,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531073117.600, "dur": 1.581, + "args": { + "External id": 1405477,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531073122.870, "dur": 89.618, + "args": { + "External id": 1405478,"Sequence number": 15109002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073124.364, "dur": 4.151, + "args": { + "External id": 1405479,"Sequence number": 15109002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073125.058, "dur": 3.324, + "args": { + "External id": 1405480,"Sequence number": 15109002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14444 + } + }, + { + "ph": "s", "id": 64, "pid": 2338710, "tid": 2338710, "ts": 6410531073125.058, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531073133.005, "dur": 74.156, + "args": { + "External id": 1405481,"Sequence number": 15109003, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14445 + } + }, + { + "ph": "s", "id": 63, "pid": 2338710, "tid": 2338710, "ts": 6410531073133.005, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073209.227, "dur": 2.566, + "args": { + "External id": 1405482,"Sequence number": 15109004, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14446 + } + }, + { + "ph": "s", "id": 62, "pid": 2338710, "tid": 2338710, "ts": 6410531073209.227, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531073222.474, "dur": 59.899, + "args": { + "External id": 1405483,"Sequence number": 15109005, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531073222.993, "dur": 5.511, + "args": { + "External id": 1405484,"Sequence number": 15109005, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14448 + } + }, + { + "ph": "s", "id": 61, "pid": 2338710, "tid": 2338710, "ts": 6410531073222.993, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531073224.948, "dur": 2.416, + "args": { + "External id": 1405485,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531073226.562, "dur": 0.660, + "args": { + "External id": 1405486,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531073230.977, "dur": 51.216, + "args": { + "External id": 1405487,"Sequence number": 15109006, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073232.026, "dur": 2.949, + "args": { + "External id": 1405488,"Sequence number": 15109006, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073232.773, "dur": 2.081, + "args": { + "External id": 1405489,"Sequence number": 15109006, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14453 + } + }, + { + "ph": "s", "id": 60, "pid": 2338710, "tid": 2338710, "ts": 6410531073232.773, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531073235.615, "dur": 42.121, + "args": { + "External id": 1405490,"Sequence number": 15109007, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14454 + } + }, + { + "ph": "s", "id": 59, "pid": 2338710, "tid": 2338710, "ts": 6410531073235.615, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073280.104, "dur": 1.728, + "args": { + "External id": 1405491,"Sequence number": 15109008, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14455 + } + }, + { + "ph": "s", "id": 58, "pid": 2338710, "tid": 2338710, "ts": 6410531073280.104, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531073292.744, "dur": 60.470, + "args": { + "External id": 1405492,"Sequence number": 15109009, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531073293.190, "dur": 7.693, + "args": { + "External id": 1405493,"Sequence number": 15109009, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14457 + } + }, + { + "ph": "s", "id": 57, "pid": 2338710, "tid": 2338710, "ts": 6410531073293.190, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531073295.228, "dur": 4.204, + "args": { + "External id": 1405494,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531073296.595, "dur": 2.433, + "args": { + "External id": 1405495,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531073301.549, "dur": 51.418, + "args": { + "External id": 1405496,"Sequence number": 15109010, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073304.783, "dur": 4.005, + "args": { + "External id": 1405497,"Sequence number": 15109010, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073305.368, "dur": 3.287, + "args": { + "External id": 1405498,"Sequence number": 15109010, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14462 + } + }, + { + "ph": "s", "id": 56, "pid": 2338710, "tid": 2338710, "ts": 6410531073305.368, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531073309.408, "dur": 37.850, + "args": { + "External id": 1405499,"Sequence number": 15109011, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14463 + } + }, + { + "ph": "s", "id": 55, "pid": 2338710, "tid": 2338710, "ts": 6410531073309.408, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073348.910, "dur": 3.711, + "args": { + "External id": 1405500,"Sequence number": 15109012, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14464 + } + }, + { + "ph": "s", "id": 54, "pid": 2338710, "tid": 2338710, "ts": 6410531073348.910, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073372.762, "dur": 3.462, + "args": { + "External id": 1405501,"Sequence number": 15109013, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073373.443, "dur": 2.655, + "args": { + "External id": 1405502,"Sequence number": 15109013, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14466 + } + }, + { + "ph": "s", "id": 53, "pid": 2338710, "tid": 2338710, "ts": 6410531073373.443, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073383.419, "dur": 4.009, + "args": { + "External id": 1405503,"Sequence number": 15109014, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073384.168, "dur": 3.152, + "args": { + "External id": 1405504,"Sequence number": 15109014, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14468 + } + }, + { + "ph": "s", "id": 52, "pid": 2338710, "tid": 2338710, "ts": 6410531073384.168, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073391.300, "dur": 4.313, + "args": { + "External id": 1405505,"Sequence number": 15109015, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073392.233, "dur": 3.271, + "args": { + "External id": 1405506,"Sequence number": 15109015, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14470 + } + }, + { + "ph": "s", "id": 51, "pid": 2338710, "tid": 2338710, "ts": 6410531073392.233, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531073444.182, "dur": 166.393, + "args": { + "External id": 1405507,"Sequence number": 15109016, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14471 + } + }, + { + "ph": "s", "id": 50, "pid": 2338710, "tid": 2338710, "ts": 6410531073444.182, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531073464.500, "dur": 11.358, + "args": { + "External id": 1405508,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531073467.091, "dur": 8.066, + "args": { + "External id": 1405509,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531073623.056, "dur": 103.353, + "args": { + "External id": 1405510,"Sequence number": 15109017, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14474 + } + }, + { + "ph": "s", "id": 49, "pid": 2338710, "tid": 2338710, "ts": 6410531073623.056, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531073635.996, "dur": 6.017, + "args": { + "External id": 1405511,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 14475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531073638.081, "dur": 3.621, + "args": { + "External id": 1405512,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338710, "tid": 2338710, + "ts": 6410531073755.318, "dur": 168.751, + "args": { + "External id": 1405513,"Sequence number": 15109018, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 14477 + } + }, + { + "ph": "s", "id": 48, "pid": 2338710, "tid": 2338710, "ts": 6410531073755.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410531073780.118, "dur": 119.656, + "args": { + "External id": 1405514,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531073827.008, "dur": 6.277, + "args": { + "External id": 1405515,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531073829.286, "dur": 3.491, + "args": { + "External id": 1405516,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531073835.696, "dur": 4.360, + "args": { + "External id": 1405517,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531073843.584, "dur": 1.072, + "args": { + "External id": 1405518,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531073847.076, "dur": 3.021, + "args": { + "External id": 1405519,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410531073911.275, "dur": 4.555, + "args": { + "External id": 1405520,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 14484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073929.044, "dur": 5.150, + "args": { + "External id": 1405521,"Sequence number": 15109019, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073930.200, "dur": 3.827, + "args": { + "External id": 1405522,"Sequence number": 15109019, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14486 + } + }, + { + "ph": "s", "id": 47, "pid": 2338710, "tid": 2338710, "ts": 6410531073930.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531073944.784, "dur": 102.558, + "args": { + "External id": 1405523,"Sequence number": 15109020, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531073945.814, "dur": 9.049, + "args": { + "External id": 1405524,"Sequence number": 15109020, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14488 + } + }, + { + "ph": "s", "id": 46, "pid": 2338710, "tid": 2338710, "ts": 6410531073945.814, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531073948.320, "dur": 5.503, + "args": { + "External id": 1405525,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531073952.289, "dur": 1.294, + "args": { + "External id": 1405526,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531073955.995, "dur": 91.081, + "args": { + "External id": 1405527,"Sequence number": 15109021, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531073957.692, "dur": 3.088, + "args": { + "External id": 1405528,"Sequence number": 15109021, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531073958.654, "dur": 2.013, + "args": { + "External id": 1405529,"Sequence number": 15109021, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14493 + } + }, + { + "ph": "s", "id": 45, "pid": 2338710, "tid": 2338710, "ts": 6410531073958.654, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531073963.636, "dur": 76.137, + "args": { + "External id": 1405530,"Sequence number": 15109022, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14494 + } + }, + { + "ph": "s", "id": 44, "pid": 2338710, "tid": 2338710, "ts": 6410531073963.636, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074042.168, "dur": 4.273, + "args": { + "External id": 1405531,"Sequence number": 15109023, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14495 + } + }, + { + "ph": "s", "id": 43, "pid": 2338710, "tid": 2338710, "ts": 6410531074042.168, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531074123.790, "dur": 214.828, + "args": { + "External id": 1405532,"Sequence number": 15109024, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 14496 + } + }, + { + "ph": "s", "id": 42, "pid": 2338710, "tid": 2338710, "ts": 6410531074123.790, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531074143.431, "dur": 7.813, + "args": { + "External id": 1405533,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074146.603, "dur": 4.270, + "args": { + "External id": 1405534,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338710, "tid": 2338710, + "ts": 6410531074155.423, "dur": 2.833, + "args": { + "External id": 1405535,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 14499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531074156.475, "dur": 1.675, + "args": { + "External id": 1405536,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074157.076, "dur": 0.973, + "args": { + "External id": 1405537,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531074165.923, "dur": 7.488, + "args": { + "External id": 1405538,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531074167.943, "dur": 5.012, + "args": { + "External id": 1405539,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531074181.772, "dur": 3.804, + "args": { + "External id": 1405540,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531074188.943, "dur": 3.338, + "args": { + "External id": 1405541,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531074317.568, "dur": 2.970, + "args": { + "External id": 1405542,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074318.637, "dur": 1.710, + "args": { + "External id": 1405543,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531074323.057, "dur": 1.989, + "args": { + "External id": 1405544,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074324.079, "dur": 0.859, + "args": { + "External id": 1405545,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531074355.720, "dur": 124.078, + "args": { + "External id": 1405546,"Sequence number": 15109025, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531074356.639, "dur": 9.166, + "args": { + "External id": 1405547,"Sequence number": 15109025, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14511 + } + }, + { + "ph": "s", "id": 41, "pid": 2338710, "tid": 2338710, "ts": 6410531074356.639, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531074360.833, "dur": 3.427, + "args": { + "External id": 1405548,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531074362.514, "dur": 1.411, + "args": { + "External id": 1405549,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531074366.649, "dur": 112.863, + "args": { + "External id": 1405550,"Sequence number": 15109026, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531074368.051, "dur": 4.658, + "args": { + "External id": 1405551,"Sequence number": 15109026, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074370.513, "dur": 2.084, + "args": { + "External id": 1405552,"Sequence number": 15109026, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14516 + } + }, + { + "ph": "s", "id": 40, "pid": 2338710, "tid": 2338710, "ts": 6410531074370.513, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531074373.614, "dur": 98.389, + "args": { + "External id": 1405553,"Sequence number": 15109027, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14517 + } + }, + { + "ph": "s", "id": 39, "pid": 2338710, "tid": 2338710, "ts": 6410531074373.614, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074475.500, "dur": 3.271, + "args": { + "External id": 1405554,"Sequence number": 15109028, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14518 + } + }, + { + "ph": "s", "id": 38, "pid": 2338710, "tid": 2338710, "ts": 6410531074475.500, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531074489.564, "dur": 81.015, + "args": { + "External id": 1405555,"Sequence number": 15109029, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531074490.215, "dur": 11.472, + "args": { + "External id": 1405556,"Sequence number": 15109029, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14520 + } + }, + { + "ph": "s", "id": 37, "pid": 2338710, "tid": 2338710, "ts": 6410531074490.215, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531074496.085, "dur": 4.525, + "args": { + "External id": 1405557,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531074497.643, "dur": 2.733, + "args": { + "External id": 1405558,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531074502.364, "dur": 67.977, + "args": { + "External id": 1405559,"Sequence number": 15109030, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531074503.412, "dur": 5.908, + "args": { + "External id": 1405560,"Sequence number": 15109030, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074504.144, "dur": 5.059, + "args": { + "External id": 1405561,"Sequence number": 15109030, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14525 + } + }, + { + "ph": "s", "id": 36, "pid": 2338710, "tid": 2338710, "ts": 6410531074504.144, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531074509.994, "dur": 53.792, + "args": { + "External id": 1405562,"Sequence number": 15109031, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14526 + } + }, + { + "ph": "s", "id": 35, "pid": 2338710, "tid": 2338710, "ts": 6410531074509.994, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074566.169, "dur": 3.707, + "args": { + "External id": 1405563,"Sequence number": 15109032, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14527 + } + }, + { + "ph": "s", "id": 34, "pid": 2338710, "tid": 2338710, "ts": 6410531074566.169, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531074592.880, "dur": 159.363, + "args": { + "External id": 1405564,"Sequence number": 15109033, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14528 + } + }, + { + "ph": "s", "id": 33, "pid": 2338710, "tid": 2338710, "ts": 6410531074592.880, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531074633.761, "dur": 4.992, + "args": { + "External id": 1405565,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531074672.329, "dur": 64.635, + "args": { + "External id": 1405566,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531074672.953, "dur": 4.609, + "args": { + "External id": 1405567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 14531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531074673.996, "dur": 2.755, + "args": { + "External id": 1405568,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 14532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531074675.524, "dur": 0.950, + "args": { + "External id": 1405569,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 14533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531074678.351, "dur": 58.221, + "args": { + "External id": 1405570,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 14534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410531074679.662, "dur": 4.082, + "args": { + "External id": 1405571,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074682.473, "dur": 1.145, + "args": { + "External id": 1405572,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531074684.304, "dur": 48.609, + "args": { + "External id": 1405573,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 14537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074735.190, "dur": 0.893, + "args": { + "External id": 1405574,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410531074761.754, "dur": 26.879, + "args": { + "External id": 1405575,"Sequence number": 15109034, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 14539 + } + }, + { + "ph": "s", "id": 32, "pid": 2338710, "tid": 2338710, "ts": 6410531074761.754, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338710, "tid": 2338710, + "ts": 6410531074806.244, "dur": 41.134, + "args": { + "External id": 1405576,"Sequence number": 15109035, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "-2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1]], []], "Input Dims": [[[8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096]], []], "Ev Idx": 14540 + } + }, + { + "ph": "s", "id": 31, "pid": 2338710, "tid": 2338710, "ts": 6410531074806.244, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338710, "tid": 2338710, + "ts": 6410531074813.653, "dur": 29.111, + "args": { + "External id": 1405577,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1]], []], "Input Dims": [[[8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096]], []], "Ev Idx": 14541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531074844.425, "dur": 1.250, + "args": { + "External id": 1405578,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 16384], []], "Ev Idx": 14542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410531074879.939, "dur": 44.461, + "args": { + "External id": 1405579,"Record function id": 0, "Ev Idx": 14543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 2338710, "tid": 2338710, + "ts": 6410531074925.436, "dur": 237.058, + "args": { + "External id": 1405580,"Record function id": 0, "Ev Idx": 14544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531074961.457, "dur": 191.232, + "args": { + "External id": 1405581,"Sequence number": 15109036, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1], [67108864, 16384, 4096, 1]], "Input Dims": [[4096], [8, 4096, 4, 4096]], "Ev Idx": 14545 + } + }, + { + "ph": "s", "id": 30, "pid": 2338710, "tid": 2338710, "ts": 6410531074961.457, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410531075025.579, "dur": 82.192, + "args": { + "External id": 1405582,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[131072, 4096], [131072, 4096], [4096], [131072], [], [], [], [], [], [], [], [], []], "Ev Idx": 14546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410531075244.733, "dur": 41.547, + "args": { + "External id": 1405583,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 14547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531075247.473, "dur": 6.375, + "args": { + "External id": 1405584,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075256.709, "dur": 29.271, + "args": { + "External id": 1405585,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 14549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075260.185, "dur": 25.009, + "args": { + "External id": 1405586,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 14550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410531075290.952, "dur": 20.554, + "args": { + "External id": 1405587,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 14551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531075292.056, "dur": 2.316, + "args": { + "External id": 1405588,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075295.145, "dur": 16.107, + "args": { + "External id": 1405589,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 14553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075298.325, "dur": 12.547, + "args": { + "External id": 1405590,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 14554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410531075314.061, "dur": 19.124, + "args": { + "External id": 1405591,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 14555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531075315.439, "dur": 3.782, + "args": { + "External id": 1405592,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075319.772, "dur": 13.054, + "args": { + "External id": 1405593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 14557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075320.638, "dur": 11.785, + "args": { + "External id": 1405594,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 14558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531075343.827, "dur": 0.636, + "args": { + "External id": 1405595,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], [], []], "Ev Idx": 14559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338710, "tid": 2338710, + "ts": 6410531075351.162, "dur": 11.150, + "args": { + "External id": 1405596,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "5", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 14560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075358.301, "dur": 2.098, + "args": { + "External id": 1405597,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 14561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075368.653, "dur": 6.826, + "args": { + "External id": 1405598,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 14562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075372.942, "dur": 0.696, + "args": { + "External id": 1405599,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 14563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075376.793, "dur": 2.649, + "args": { + "External id": 1405600,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 14564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075378.222, "dur": 0.503, + "args": { + "External id": 1405601,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 14565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075381.164, "dur": 2.429, + "args": { + "External id": 1405602,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 14566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075382.635, "dur": 0.410, + "args": { + "External id": 1405603,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 14567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075386.379, "dur": 4.806, + "args": { + "External id": 1405604,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 4], [], [], [], []], "Ev Idx": 14568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075388.043, "dur": 2.577, + "args": { + "External id": 1405605,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 4], [], [], []], "Ev Idx": 14569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075392.642, "dur": 2.843, + "args": { + "External id": 1405606,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 4], [], [], [], []], "Ev Idx": 14570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075394.385, "dur": 0.300, + "args": { + "External id": 1405607,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 4], [], [], []], "Ev Idx": 14571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075396.536, "dur": 2.470, + "args": { + "External id": 1405608,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4096, 4], [], [], [], []], "Ev Idx": 14572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075398.069, "dur": 0.427, + "args": { + "External id": 1405609,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4096, 4], [], [], []], "Ev Idx": 14573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531075403.547, "dur": 4.535, + "args": { + "External id": 1405610,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4096, 4], [], []], "Ev Idx": 14574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075406.705, "dur": 0.518, + "args": { + "External id": 1405611,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4096, 4], [], [], []], "Ev Idx": 14575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075412.181, "dur": 16.547, + "args": { + "External id": 1405612,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 14576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075414.017, "dur": 0.355, + "args": { + "External id": 1405613,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 14577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410531075432.921, "dur": 8.159, + "args": { + "External id": 1405614,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 14578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075439.318, "dur": 0.722, + "args": { + "External id": 1405615,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 14579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075442.778, "dur": 2.906, + "args": { + "External id": 1405616,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 14580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075444.453, "dur": 0.626, + "args": { + "External id": 1405617,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 14581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075449.152, "dur": 6.357, + "args": { + "External id": 1405618,"Sequence number": 15109037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 14582 + } + }, + { + "ph": "s", "id": 29, "pid": 2338710, "tid": 2338710, "ts": 6410531075449.152, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075453.257, "dur": 0.464, + "args": { + "External id": 1405619,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 14583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075458.850, "dur": 6.537, + "args": { + "External id": 1405620,"Sequence number": 15109038, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 14584 + } + }, + { + "ph": "s", "id": 28, "pid": 2338710, "tid": 2338710, "ts": 6410531075458.850, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075462.175, "dur": 2.457, + "args": { + "External id": 1405621,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 14585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410531075466.417, "dur": 4.660, + "args": { + "External id": 1405622,"Sequence number": 15109039, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 14586 + } + }, + { + "ph": "s", "id": 27, "pid": 2338710, "tid": 2338710, "ts": 6410531075466.417, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075469.703, "dur": 0.473, + "args": { + "External id": 1405623,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 14587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531075472.270, "dur": 3.999, + "args": { + "External id": 1405624,"Sequence number": 15109040, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 14588 + } + }, + { + "ph": "s", "id": 26, "pid": 2338710, "tid": 2338710, "ts": 6410531075472.270, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075474.783, "dur": 0.779, + "args": { + "External id": 1405625,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 14589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410531075480.466, "dur": 42.657, + "args": { + "External id": 1405626,"Sequence number": 15109041, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 14590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410531075484.351, "dur": 38.531, + "args": { + "External id": 1405627,"Sequence number": 15109041, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 14591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531075487.172, "dur": 7.750, + "args": { + "External id": 1405628,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 14592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531075489.045, "dur": 5.240, + "args": { + "External id": 1405629,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075496.439, "dur": 25.931, + "args": { + "External id": 1405630,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 14594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531075546.088, "dur": 5.492, + "args": { + "External id": 1405631,"Sequence number": 15109041, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14595 + } + }, + { + "ph": "s", "id": 25, "pid": 2338710, "tid": 2338710, "ts": 6410531075546.088, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531075553.768, "dur": 1.011, + "args": { + "External id": 1405632,"Sequence number": 15109042, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 14596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531075583.462, "dur": 133465.868, + "args": { + "External id": 1405633,"Sequence number": 15109042, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 14597 + } + }, + { + "ph": "s", "id": 24, "pid": 2338710, "tid": 2338710, "ts": 6410531075583.462, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410531075597.553, "dur": 27.959, + "args": { + "External id": 1405634,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410531075598.319, "dur": 26.969, + "args": { + "External id": 1405635,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531075599.765, "dur": 4.754, + "args": { + "External id": 1405636,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531075600.893, "dur": 3.233, + "args": { + "External id": 1405637,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075605.599, "dur": 19.259, + "args": { + "External id": 1405638,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 14602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531075641.656, "dur": 24.503, + "args": { + "External id": 1405639,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531075642.955, "dur": 5.772, + "args": { + "External id": 1405640,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075645.109, "dur": 3.312, + "args": { + "External id": 1405641,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075649.827, "dur": 16.125, + "args": { + "External id": 1405642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 14606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075650.809, "dur": 14.750, + "args": { + "External id": 1405643,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531075669.729, "dur": 22.072, + "args": { + "External id": 1405644,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 14608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531075670.365, "dur": 7.413, + "args": { + "External id": 1405645,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 14609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075673.800, "dur": 3.747, + "args": { + "External id": 1405646,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075678.287, "dur": 13.319, + "args": { + "External id": 1405647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075678.781, "dur": 12.490, + "args": { + "External id": 1405648,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 14612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410531075696.108, "dur": 18.511, + "args": { + "External id": 1405649,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 14613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531075699.013, "dur": 2.689, + "args": { + "External id": 1405650,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075702.257, "dur": 12.094, + "args": { + "External id": 1405651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 14615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075702.765, "dur": 11.208, + "args": { + "External id": 1405652,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 14616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410531075722.908, "dur": 25.181, + "args": { + "External id": 1405653,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 14617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531075752.552, "dur": 66.577, + "args": { + "External id": 1405654,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 14618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531075755.666, "dur": 62.995, + "args": { + "External id": 1405655,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075761.916, "dur": 0.737, + "args": { + "External id": 1405656,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 14620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531075763.977, "dur": 35.101, + "args": { + "External id": 1405657,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531075765.714, "dur": 33.097, + "args": { + "External id": 1405658,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 14622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531075778.793, "dur": 2.779, + "args": { + "External id": 1405659,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531075782.397, "dur": 16.001, + "args": { + "External id": 1405660,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 14624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410531075824.047, "dur": 126901.174, + "args": { + "External id": 1405661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 14625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410531075825.896, "dur": 126896.218, + "args": { + "External id": 1405662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 14626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531202749.892, "dur": 14.363, + "args": { + "External id": 1405663,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531202759.591, "dur": 1.797, + "args": { + "External id": 1405664,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531202770.814, "dur": 125.721, + "args": { + "External id": 1405665,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531202772.397, "dur": 7.184, + "args": { + "External id": 1405666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531202775.424, "dur": 3.321, + "args": { + "External id": 1405667,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531202777.367, "dur": 1.110, + "args": { + "External id": 1405668,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531202781.075, "dur": 114.805, + "args": { + "External id": 1405669,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531202790.084, "dur": 104.799, + "args": { + "External id": 1405670,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531202901.031, "dur": 4.533, + "args": { + "External id": 1405671,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531202903.283, "dur": 0.625, + "args": { + "External id": 1405672,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531202916.328, "dur": 5.976, + "args": { + "External id": 1405673,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531202935.531, "dur": 8.289, + "args": { + "External id": 1405674,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531202938.103, "dur": 5.429, + "args": { + "External id": 1405675,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531203128.355, "dur": 230.213, + "args": { + "External id": 1405676,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531203133.492, "dur": 3.501, + "args": { + "External id": 1405677,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531203139.502, "dur": 218.393, + "args": { + "External id": 1405678,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531203142.406, "dur": 0.650, + "args": { + "External id": 1405679,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531203145.109, "dur": 29.714, + "args": { + "External id": 1405680,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531203177.164, "dur": 5.565, + "args": { + "External id": 1405681,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531203181.558, "dur": 0.844, + "args": { + "External id": 1405682,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531203184.591, "dur": 28.366, + "args": { + "External id": 1405683,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531203186.299, "dur": 1.285, + "args": { + "External id": 1405684,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531203192.324, "dur": 20.309, + "args": { + "External id": 1405685,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531203196.987, "dur": 3.348, + "args": { + "External id": 1405686,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531203219.578, "dur": 24.494, + "args": { + "External id": 1405687,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531203246.870, "dur": 18.932, + "args": { + "External id": 1405688,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531203269.855, "dur": 15.296, + "args": { + "External id": 1405689,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531203287.584, "dur": 13.929, + "args": { + "External id": 1405690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531203304.477, "dur": 23.269, + "args": { + "External id": 1405691,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531203307.031, "dur": 1.484, + "args": { + "External id": 1405692,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531203312.667, "dur": 0.464, + "args": { + "External id": 1405693,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531203330.929, "dur": 13.271, + "args": { + "External id": 1405694,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531203346.058, "dur": 10.752, + "args": { + "External id": 1405695,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531203366.726, "dur": 2.443, + "args": { + "External id": 1405696,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531203377.245, "dur": 4.813, + "args": { + "External id": 1405697,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531203380.489, "dur": 0.561, + "args": { + "External id": 1405698,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531203487.042, "dur": 85.861, + "args": { + "External id": 1405699,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531203581.493, "dur": 11.560, + "args": { + "External id": 1405700,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531203588.768, "dur": 1.125, + "args": { + "External id": 1405701,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531203595.584, "dur": 38.487, + "args": { + "External id": 1405702,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531203644.206, "dur": 10.328, + "args": { + "External id": 1405703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531203646.889, "dur": 6.628, + "args": { + "External id": 1405704,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531203649.751, "dur": 3.353, + "args": { + "External id": 1405705,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531203660.145, "dur": 63.634, + "args": { + "External id": 1405706,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531203664.533, "dur": 58.713, + "args": { + "External id": 1405707,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531203732.316, "dur": 19.184, + "args": { + "External id": 1405708,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531203759.550, "dur": 4.829, + "args": { + "External id": 1405709,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531203762.507, "dur": 0.615, + "args": { + "External id": 1405710,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531203769.260, "dur": 52.158, + "args": { + "External id": 1405711,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531203770.372, "dur": 6.614, + "args": { + "External id": 1405712,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531203771.456, "dur": 4.680, + "args": { + "External id": 1405713,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531203775.393, "dur": 0.547, + "args": { + "External id": 1405714,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531203777.949, "dur": 43.091, + "args": { + "External id": 1405715,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531203778.908, "dur": 41.459, + "args": { + "External id": 1405716,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531203826.121, "dur": 4.208, + "args": { + "External id": 1405717,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531203828.427, "dur": 0.669, + "args": { + "External id": 1405718,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531203838.733, "dur": 2.263, + "args": { + "External id": 1405719,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531203853.400, "dur": 9.997, + "args": { + "External id": 1405720,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531203855.936, "dur": 7.164, + "args": { + "External id": 1405721,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531203997.575, "dur": 280.111, + "args": { + "External id": 1405722,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531204001.444, "dur": 4.118, + "args": { + "External id": 1405723,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531204007.777, "dur": 269.283, + "args": { + "External id": 1405724,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531204010.217, "dur": 0.473, + "args": { + "External id": 1405725,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531204013.040, "dur": 33.896, + "args": { + "External id": 1405726,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531204051.910, "dur": 49.357, + "args": { + "External id": 1405727,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204099.389, "dur": 1.241, + "args": { + "External id": 1405728,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531204102.426, "dur": 31.471, + "args": { + "External id": 1405729,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531204103.848, "dur": 2.472, + "args": { + "External id": 1405730,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531204107.898, "dur": 25.568, + "args": { + "External id": 1405731,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204113.957, "dur": 2.857, + "args": { + "External id": 1405732,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531204135.780, "dur": 26.542, + "args": { + "External id": 1405733,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204164.346, "dur": 14.865, + "args": { + "External id": 1405734,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531204182.671, "dur": 17.920, + "args": { + "External id": 1405735,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204202.278, "dur": 14.448, + "args": { + "External id": 1405736,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531204218.552, "dur": 27.099, + "args": { + "External id": 1405737,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204223.298, "dur": 2.345, + "args": { + "External id": 1405738,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204227.657, "dur": 0.572, + "args": { + "External id": 1405739,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204247.617, "dur": 13.389, + "args": { + "External id": 1405740,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204262.517, "dur": 13.304, + "args": { + "External id": 1405741,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531204288.911, "dur": 3.126, + "args": { + "External id": 1405742,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531204304.045, "dur": 4.340, + "args": { + "External id": 1405743,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204306.960, "dur": 0.438, + "args": { + "External id": 1405744,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531204401.644, "dur": 94.547, + "args": { + "External id": 1405745,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531204503.933, "dur": 6.211, + "args": { + "External id": 1405746,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204507.644, "dur": 0.869, + "args": { + "External id": 1405747,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204512.008, "dur": 31.132, + "args": { + "External id": 1405748,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531204548.926, "dur": 8.289, + "args": { + "External id": 1405749,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531204550.796, "dur": 5.731, + "args": { + "External id": 1405750,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204555.101, "dur": 1.190, + "args": { + "External id": 1405751,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531204561.152, "dur": 47.490, + "args": { + "External id": 1405752,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531204562.295, "dur": 45.734, + "args": { + "External id": 1405753,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204613.548, "dur": 16.897, + "args": { + "External id": 1405754,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531204637.552, "dur": 3.947, + "args": { + "External id": 1405755,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204639.977, "dur": 0.641, + "args": { + "External id": 1405756,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531204646.080, "dur": 51.868, + "args": { + "External id": 1405757,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531204649.073, "dur": 3.792, + "args": { + "External id": 1405758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531204649.808, "dur": 2.257, + "args": { + "External id": 1405759,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204651.021, "dur": 0.857, + "args": { + "External id": 1405760,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531204653.777, "dur": 43.781, + "args": { + "External id": 1405761,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531204654.370, "dur": 42.559, + "args": { + "External id": 1405762,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531204702.378, "dur": 7.835, + "args": { + "External id": 1405763,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204704.358, "dur": 4.744, + "args": { + "External id": 1405764,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531204720.133, "dur": 1.969, + "args": { + "External id": 1405765,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531204731.948, "dur": 7.193, + "args": { + "External id": 1405766,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531204734.372, "dur": 4.434, + "args": { + "External id": 1405767,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531204841.248, "dur": 313.967, + "args": { + "External id": 1405768,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531204843.453, "dur": 2.201, + "args": { + "External id": 1405769,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531204847.387, "dur": 307.256, + "args": { + "External id": 1405770,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531204850.825, "dur": 0.394, + "args": { + "External id": 1405771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531204852.402, "dur": 23.839, + "args": { + "External id": 1405772,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531204878.162, "dur": 2.989, + "args": { + "External id": 1405773,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531204880.152, "dur": 0.763, + "args": { + "External id": 1405774,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531204882.049, "dur": 26.381, + "args": { + "External id": 1405775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531204883.386, "dur": 1.437, + "args": { + "External id": 1405776,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531204885.934, "dur": 22.201, + "args": { + "External id": 1405777,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204890.533, "dur": 3.171, + "args": { + "External id": 1405778,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531204910.112, "dur": 23.960, + "args": { + "External id": 1405779,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531204936.213, "dur": 38.995, + "args": { + "External id": 1405780,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531204980.410, "dur": 37.100, + "args": { + "External id": 1405781,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205019.306, "dur": 27.966, + "args": { + "External id": 1405782,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531205049.190, "dur": 75.741, + "args": { + "External id": 1405783,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205051.067, "dur": 50.917, + "args": { + "External id": 1405784,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205105.843, "dur": 0.939, + "args": { + "External id": 1405785,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205126.928, "dur": 12.657, + "args": { + "External id": 1405786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205143.012, "dur": 10.282, + "args": { + "External id": 1405787,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531205164.442, "dur": 2.800, + "args": { + "External id": 1405788,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531205177.496, "dur": 4.065, + "args": { + "External id": 1405789,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205179.938, "dur": 0.660, + "args": { + "External id": 1405790,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531205257.976, "dur": 62.370, + "args": { + "External id": 1405791,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531205325.732, "dur": 5.235, + "args": { + "External id": 1405792,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205328.770, "dur": 1.038, + "args": { + "External id": 1405793,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205332.673, "dur": 24.698, + "args": { + "External id": 1405794,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531205364.397, "dur": 5.195, + "args": { + "External id": 1405795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531205365.961, "dur": 2.900, + "args": { + "External id": 1405796,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205367.673, "dur": 0.953, + "args": { + "External id": 1405797,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531205372.600, "dur": 57.566, + "args": { + "External id": 1405798,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531205373.577, "dur": 55.683, + "args": { + "External id": 1405799,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205436.066, "dur": 17.949, + "args": { + "External id": 1405800,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531205460.946, "dur": 6.679, + "args": { + "External id": 1405801,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205465.801, "dur": 0.625, + "args": { + "External id": 1405802,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531205471.880, "dur": 52.813, + "args": { + "External id": 1405803,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531205472.613, "dur": 5.378, + "args": { + "External id": 1405804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531205473.342, "dur": 3.978, + "args": { + "External id": 1405805,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205476.493, "dur": 0.667, + "args": { + "External id": 1405806,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531205478.734, "dur": 45.559, + "args": { + "External id": 1405807,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531205481.677, "dur": 41.740, + "args": { + "External id": 1405808,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531205529.001, "dur": 6.032, + "args": { + "External id": 1405809,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205531.383, "dur": 2.532, + "args": { + "External id": 1405810,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531205541.594, "dur": 1.804, + "args": { + "External id": 1405811,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531205552.518, "dur": 6.609, + "args": { + "External id": 1405812,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531205554.680, "dur": 4.162, + "args": { + "External id": 1405813,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531205652.712, "dur": 180.977, + "args": { + "External id": 1405814,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531205655.008, "dur": 1.804, + "args": { + "External id": 1405815,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531205658.494, "dur": 174.664, + "args": { + "External id": 1405816,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531205661.609, "dur": 0.374, + "args": { + "External id": 1405817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531205663.445, "dur": 20.243, + "args": { + "External id": 1405818,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531205685.287, "dur": 3.154, + "args": { + "External id": 1405819,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205687.445, "dur": 0.714, + "args": { + "External id": 1405820,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531205689.382, "dur": 24.293, + "args": { + "External id": 1405821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531205691.972, "dur": 1.364, + "args": { + "External id": 1405822,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531205696.675, "dur": 16.705, + "args": { + "External id": 1405823,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205699.353, "dur": 2.394, + "args": { + "External id": 1405824,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531205715.113, "dur": 23.180, + "args": { + "External id": 1405825,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205740.152, "dur": 12.860, + "args": { + "External id": 1405826,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531205756.053, "dur": 13.847, + "args": { + "External id": 1405827,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205771.326, "dur": 11.732, + "args": { + "External id": 1405828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531205784.765, "dur": 19.743, + "args": { + "External id": 1405829,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205786.738, "dur": 1.947, + "args": { + "External id": 1405830,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205790.922, "dur": 0.672, + "args": { + "External id": 1405831,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205807.919, "dur": 11.544, + "args": { + "External id": 1405832,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205820.516, "dur": 11.550, + "args": { + "External id": 1405833,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531205840.505, "dur": 1.626, + "args": { + "External id": 1405834,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531205850.162, "dur": 3.189, + "args": { + "External id": 1405835,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205852.216, "dur": 0.369, + "args": { + "External id": 1405836,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531205915.672, "dur": 51.269, + "args": { + "External id": 1405837,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531205971.894, "dur": 6.597, + "args": { + "External id": 1405838,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531205974.601, "dur": 2.794, + "args": { + "External id": 1405839,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531205982.469, "dur": 25.418, + "args": { + "External id": 1405840,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531206012.447, "dur": 4.849, + "args": { + "External id": 1405841,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531206013.881, "dur": 2.751, + "args": { + "External id": 1405842,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206015.570, "dur": 0.837, + "args": { + "External id": 1405843,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531206019.747, "dur": 81.015, + "args": { + "External id": 1405844,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531206021.126, "dur": 78.289, + "args": { + "External id": 1405845,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206106.965, "dur": 18.781, + "args": { + "External id": 1405846,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531206135.061, "dur": 4.707, + "args": { + "External id": 1405847,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206137.818, "dur": 0.785, + "args": { + "External id": 1405848,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531206143.870, "dur": 52.874, + "args": { + "External id": 1405849,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531206144.839, "dur": 3.979, + "args": { + "External id": 1405850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531206145.928, "dur": 2.210, + "args": { + "External id": 1405851,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206147.181, "dur": 0.826, + "args": { + "External id": 1405852,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531206151.605, "dur": 44.835, + "args": { + "External id": 1405853,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531206152.447, "dur": 43.434, + "args": { + "External id": 1405854,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531206201.199, "dur": 6.502, + "args": { + "External id": 1405855,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206203.505, "dur": 3.084, + "args": { + "External id": 1405856,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531206214.154, "dur": 1.502, + "args": { + "External id": 1405857,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531206223.868, "dur": 8.953, + "args": { + "External id": 1405858,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531206227.998, "dur": 4.559, + "args": { + "External id": 1405859,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531206322.108, "dur": 216.707, + "args": { + "External id": 1405860,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531206324.058, "dur": 3.202, + "args": { + "External id": 1405861,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531206328.787, "dur": 209.536, + "args": { + "External id": 1405862,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531206330.088, "dur": 0.349, + "args": { + "External id": 1405863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531206331.746, "dur": 21.415, + "args": { + "External id": 1405864,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531206355.205, "dur": 5.792, + "args": { + "External id": 1405865,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206359.976, "dur": 0.765, + "args": { + "External id": 1405866,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531206361.814, "dur": 25.141, + "args": { + "External id": 1405867,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531206365.385, "dur": 1.765, + "args": { + "External id": 1405868,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531206368.248, "dur": 18.447, + "args": { + "External id": 1405869,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206370.517, "dur": 2.885, + "args": { + "External id": 1405870,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531206388.106, "dur": 23.458, + "args": { + "External id": 1405871,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206413.343, "dur": 31.538, + "args": { + "External id": 1405872,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531206449.076, "dur": 16.153, + "args": { + "External id": 1405873,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206466.652, "dur": 15.223, + "args": { + "External id": 1405874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531206483.737, "dur": 26.021, + "args": { + "External id": 1405875,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206486.150, "dur": 1.920, + "args": { + "External id": 1405876,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206492.038, "dur": 2.423, + "args": { + "External id": 1405877,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206511.576, "dur": 13.248, + "args": { + "External id": 1405878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206525.756, "dur": 11.417, + "args": { + "External id": 1405879,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531206546.525, "dur": 2.184, + "args": { + "External id": 1405880,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531206558.277, "dur": 3.557, + "args": { + "External id": 1405881,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206560.632, "dur": 0.442, + "args": { + "External id": 1405882,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531206634.928, "dur": 58.454, + "args": { + "External id": 1405883,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531206700.461, "dur": 4.568, + "args": { + "External id": 1405884,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206703.169, "dur": 0.656, + "args": { + "External id": 1405885,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206706.615, "dur": 22.607, + "args": { + "External id": 1405886,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531206734.195, "dur": 5.994, + "args": { + "External id": 1405887,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531206735.618, "dur": 3.868, + "args": { + "External id": 1405888,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206737.635, "dur": 1.670, + "args": { + "External id": 1405889,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531206745.340, "dur": 43.553, + "args": { + "External id": 1405890,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531206746.813, "dur": 41.353, + "args": { + "External id": 1405891,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531206792.745, "dur": 14.899, + "args": { + "External id": 1405892,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531206813.296, "dur": 3.753, + "args": { + "External id": 1405893,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206815.325, "dur": 0.955, + "args": { + "External id": 1405894,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531206821.182, "dur": 46.266, + "args": { + "External id": 1405895,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531206821.828, "dur": 5.970, + "args": { + "External id": 1405896,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531206825.216, "dur": 1.994, + "args": { + "External id": 1405897,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206826.467, "dur": 0.608, + "args": { + "External id": 1405898,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531206828.581, "dur": 38.542, + "args": { + "External id": 1405899,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531206829.127, "dur": 37.337, + "args": { + "External id": 1405900,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531206871.952, "dur": 5.460, + "args": { + "External id": 1405901,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531206874.145, "dur": 2.237, + "args": { + "External id": 1405902,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531206883.834, "dur": 1.468, + "args": { + "External id": 1405903,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531206916.249, "dur": 8.969, + "args": { + "External id": 1405904,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531206918.421, "dur": 6.500, + "args": { + "External id": 1405905,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531207014.448, "dur": 245.266, + "args": { + "External id": 1405906,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531207016.411, "dur": 2.256, + "args": { + "External id": 1405907,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531207020.206, "dur": 238.799, + "args": { + "External id": 1405908,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531207021.514, "dur": 0.307, + "args": { + "External id": 1405909,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531207025.208, "dur": 23.181, + "args": { + "External id": 1405910,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531207049.977, "dur": 3.048, + "args": { + "External id": 1405911,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207052.085, "dur": 0.698, + "args": { + "External id": 1405912,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531207053.839, "dur": 79.676, + "args": { + "External id": 1405913,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531207054.923, "dur": 52.762, + "args": { + "External id": 1405914,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531207110.073, "dur": 23.126, + "args": { + "External id": 1405915,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207116.148, "dur": 3.117, + "args": { + "External id": 1405916,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531207135.128, "dur": 24.208, + "args": { + "External id": 1405917,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207161.434, "dur": 13.031, + "args": { + "External id": 1405918,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531207177.454, "dur": 13.583, + "args": { + "External id": 1405919,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207192.605, "dur": 12.194, + "args": { + "External id": 1405920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531207212.162, "dur": 20.364, + "args": { + "External id": 1405921,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207214.216, "dur": 1.889, + "args": { + "External id": 1405922,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207218.568, "dur": 0.686, + "args": { + "External id": 1405923,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207233.816, "dur": 11.612, + "args": { + "External id": 1405924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207246.714, "dur": 11.156, + "args": { + "External id": 1405925,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531207268.879, "dur": 2.658, + "args": { + "External id": 1405926,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531207281.905, "dur": 4.191, + "args": { + "External id": 1405927,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207284.674, "dur": 0.553, + "args": { + "External id": 1405928,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531207359.173, "dur": 79.910, + "args": { + "External id": 1405929,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531207445.825, "dur": 5.787, + "args": { + "External id": 1405930,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207449.210, "dur": 0.881, + "args": { + "External id": 1405931,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207453.317, "dur": 30.120, + "args": { + "External id": 1405932,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531207488.303, "dur": 9.961, + "args": { + "External id": 1405933,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531207489.865, "dur": 7.516, + "args": { + "External id": 1405934,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207494.292, "dur": 2.810, + "args": { + "External id": 1405935,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531207501.563, "dur": 47.069, + "args": { + "External id": 1405936,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531207502.441, "dur": 45.545, + "args": { + "External id": 1405937,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207552.664, "dur": 16.770, + "args": { + "External id": 1405938,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531207576.182, "dur": 4.002, + "args": { + "External id": 1405939,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207578.547, "dur": 0.684, + "args": { + "External id": 1405940,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531207584.642, "dur": 48.525, + "args": { + "External id": 1405941,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531207587.984, "dur": 3.774, + "args": { + "External id": 1405942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531207589.212, "dur": 1.878, + "args": { + "External id": 1405943,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207590.443, "dur": 0.489, + "args": { + "External id": 1405944,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531207592.545, "dur": 40.173, + "args": { + "External id": 1405945,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531207593.370, "dur": 38.687, + "args": { + "External id": 1405946,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531207637.552, "dur": 5.405, + "args": { + "External id": 1405947,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207639.272, "dur": 2.513, + "args": { + "External id": 1405948,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531207651.764, "dur": 1.799, + "args": { + "External id": 1405949,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531207662.070, "dur": 6.418, + "args": { + "External id": 1405950,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531207663.981, "dur": 4.217, + "args": { + "External id": 1405951,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531207757.722, "dur": 220.368, + "args": { + "External id": 1405952,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531207783.273, "dur": 2.585, + "args": { + "External id": 1405953,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531207789.776, "dur": 187.832, + "args": { + "External id": 1405954,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531207793.194, "dur": 0.411, + "args": { + "External id": 1405955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531207794.772, "dur": 22.831, + "args": { + "External id": 1405956,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531207819.485, "dur": 4.047, + "args": { + "External id": 1405957,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207821.469, "dur": 1.805, + "args": { + "External id": 1405958,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531207824.544, "dur": 22.946, + "args": { + "External id": 1405959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531207825.317, "dur": 1.367, + "args": { + "External id": 1405960,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531207827.603, "dur": 19.600, + "args": { + "External id": 1405961,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207829.929, "dur": 3.156, + "args": { + "External id": 1405962,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531207849.041, "dur": 21.977, + "args": { + "External id": 1405963,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207872.571, "dur": 15.263, + "args": { + "External id": 1405964,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531207892.924, "dur": 14.928, + "args": { + "External id": 1405965,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207909.138, "dur": 13.446, + "args": { + "External id": 1405966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531207924.577, "dur": 23.054, + "args": { + "External id": 1405967,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207926.254, "dur": 1.658, + "args": { + "External id": 1405968,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207929.625, "dur": 2.965, + "args": { + "External id": 1405969,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207948.967, "dur": 13.204, + "args": { + "External id": 1405970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531207965.252, "dur": 11.198, + "args": { + "External id": 1405971,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531207985.258, "dur": 1.551, + "args": { + "External id": 1405972,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531207995.475, "dur": 3.199, + "args": { + "External id": 1405973,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531207997.561, "dur": 0.277, + "args": { + "External id": 1405974,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531208106.291, "dur": 62.952, + "args": { + "External id": 1405975,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531208175.425, "dur": 5.801, + "args": { + "External id": 1405976,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208178.833, "dur": 0.836, + "args": { + "External id": 1405977,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208182.612, "dur": 25.533, + "args": { + "External id": 1405978,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531208215.141, "dur": 5.591, + "args": { + "External id": 1405979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531208216.639, "dur": 3.420, + "args": { + "External id": 1405980,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208218.212, "dur": 1.686, + "args": { + "External id": 1405981,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531208223.512, "dur": 44.224, + "args": { + "External id": 1405982,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531208224.838, "dur": 42.295, + "args": { + "External id": 1405983,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208271.807, "dur": 19.939, + "args": { + "External id": 1405984,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531208297.893, "dur": 5.866, + "args": { + "External id": 1405985,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208302.197, "dur": 0.717, + "args": { + "External id": 1405986,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531208307.904, "dur": 46.365, + "args": { + "External id": 1405987,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531208308.820, "dur": 3.456, + "args": { + "External id": 1405988,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531208309.534, "dur": 2.124, + "args": { + "External id": 1405989,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208310.614, "dur": 0.895, + "args": { + "External id": 1405990,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531208313.125, "dur": 40.765, + "args": { + "External id": 1405991,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531208315.950, "dur": 37.274, + "args": { + "External id": 1405992,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531208358.548, "dur": 5.740, + "args": { + "External id": 1405993,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208360.434, "dur": 2.742, + "args": { + "External id": 1405994,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531208370.457, "dur": 1.535, + "args": { + "External id": 1405995,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531208380.548, "dur": 6.262, + "args": { + "External id": 1405996,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531208382.821, "dur": 3.658, + "args": { + "External id": 1405997,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531208498.592, "dur": 196.667, + "args": { + "External id": 1405998,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531208503.199, "dur": 3.158, + "args": { + "External id": 1405999,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531208507.917, "dur": 186.629, + "args": { + "External id": 1406000,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531208509.624, "dur": 0.325, + "args": { + "External id": 1406001,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531208511.106, "dur": 22.937, + "args": { + "External id": 1406002,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531208535.960, "dur": 5.248, + "args": { + "External id": 1406003,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208540.139, "dur": 0.714, + "args": { + "External id": 1406004,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531208542.287, "dur": 23.192, + "args": { + "External id": 1406005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531208543.220, "dur": 1.476, + "args": { + "External id": 1406006,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531208547.919, "dur": 17.297, + "args": { + "External id": 1406007,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208550.379, "dur": 2.534, + "args": { + "External id": 1406008,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531208566.911, "dur": 24.773, + "args": { + "External id": 1406009,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208592.986, "dur": 13.613, + "args": { + "External id": 1406010,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531208609.790, "dur": 15.142, + "args": { + "External id": 1406011,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208626.095, "dur": 14.184, + "args": { + "External id": 1406012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531208642.045, "dur": 23.631, + "args": { + "External id": 1406013,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208646.360, "dur": 1.753, + "args": { + "External id": 1406014,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208650.253, "dur": 0.513, + "args": { + "External id": 1406015,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208669.244, "dur": 11.657, + "args": { + "External id": 1406016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208681.950, "dur": 11.640, + "args": { + "External id": 1406017,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531208702.091, "dur": 2.095, + "args": { + "External id": 1406018,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531208713.112, "dur": 3.514, + "args": { + "External id": 1406019,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208715.490, "dur": 0.357, + "args": { + "External id": 1406020,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531208779.235, "dur": 59.742, + "args": { + "External id": 1406021,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531208843.878, "dur": 4.288, + "args": { + "External id": 1406022,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208846.529, "dur": 0.694, + "args": { + "External id": 1406023,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208851.608, "dur": 23.099, + "args": { + "External id": 1406024,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531208878.567, "dur": 5.201, + "args": { + "External id": 1406025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531208880.014, "dur": 3.127, + "args": { + "External id": 1406026,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208881.307, "dur": 1.694, + "args": { + "External id": 1406027,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531208886.056, "dur": 41.408, + "args": { + "External id": 1406028,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531208887.212, "dur": 39.596, + "args": { + "External id": 1406029,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208931.369, "dur": 13.106, + "args": { + "External id": 1406030,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531208950.732, "dur": 21.824, + "args": { + "External id": 1406031,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 14995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531208953.135, "dur": 19.028, + "args": { + "External id": 1406032,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208957.843, "dur": 0.598, + "args": { + "External id": 1406033,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 14997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531208978.021, "dur": 28.040, + "args": { + "External id": 1406034,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 14998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531208979.818, "dur": 26.015, + "args": { + "External id": 1406035,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 14999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531208984.332, "dur": 3.738, + "args": { + "External id": 1406036,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531208989.407, "dur": 15.958, + "args": { + "External id": 1406037,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531209017.565, "dur": 7.205, + "args": { + "External id": 1406038,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531209021.960, "dur": 2.562, + "args": { + "External id": 1406039,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531209025.738, "dur": 1.133, + "args": { + "External id": 1406040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531209026.339, "dur": 0.435, + "args": { + "External id": 1406041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209121.633, "dur": 36.064, + "args": { + "External id": 1406042,"Sequence number": 15109043, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15006 + } + }, + { + "ph": "s", "id": 23, "pid": 2338710, "tid": 2338710, "ts": 6410531209121.633, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531209165.406, "dur": 7.516, + "args": { + "External id": 1406043,"Sequence number": 15109044, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 15007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209169.915, "dur": 1.334, + "args": { + "External id": 1406044,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410531209175.283, "dur": 7.604, + "args": { + "External id": 1406045,"Sequence number": 15109044, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "1"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 15009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209181.252, "dur": 0.429, + "args": { + "External id": 1406046,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531209184.229, "dur": 2.298, + "args": { + "External id": 1406047,"Sequence number": 15109044, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 15011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209185.614, "dur": 0.284, + "args": { + "External id": 1406048,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 15012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531209190.757, "dur": 5.625, + "args": { + "External id": 1406049,"Sequence number": 15109044, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15013 + } + }, + { + "ph": "s", "id": 22, "pid": 2338710, "tid": 2338710, "ts": 6410531209190.757, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209194.147, "dur": 0.820, + "args": { + "External id": 1406050,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531209200.001, "dur": 4.486, + "args": { + "External id": 1406051,"Sequence number": 15109045, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15015 + } + }, + { + "ph": "s", "id": 21, "pid": 2338710, "tid": 2338710, "ts": 6410531209200.001, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209203.101, "dur": 0.479, + "args": { + "External id": 1406052,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410531209205.579, "dur": 4.521, + "args": { + "External id": 1406053,"Sequence number": 15109046, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 15017 + } + }, + { + "ph": "s", "id": 20, "pid": 2338710, "tid": 2338710, "ts": 6410531209205.579, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209208.505, "dur": 0.745, + "args": { + "External id": 1406054,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531209211.234, "dur": 6.317, + "args": { + "External id": 1406055,"Sequence number": 15109047, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 15019 + } + }, + { + "ph": "s", "id": 19, "pid": 2338710, "tid": 2338710, "ts": 6410531209211.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209213.873, "dur": 2.878, + "args": { + "External id": 1406056,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 15020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410531209221.685, "dur": 35.901, + "args": { + "External id": 1406057,"Sequence number": 15109048, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410531209225.577, "dur": 31.781, + "args": { + "External id": 1406058,"Sequence number": 15109048, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531209228.287, "dur": 9.067, + "args": { + "External id": 1406059,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 15023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531209230.485, "dur": 6.172, + "args": { + "External id": 1406060,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209238.301, "dur": 18.672, + "args": { + "External id": 1406061,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 15025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531209283.066, "dur": 3.690, + "args": { + "External id": 1406062,"Sequence number": 15109048, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 15026 + } + }, + { + "ph": "s", "id": 18, "pid": 2338710, "tid": 2338710, "ts": 6410531209283.066, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531209288.938, "dur": 0.869, + "args": { + "External id": 1406063,"Sequence number": 15109049, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531209324.946, "dur": 47080.351, + "args": { + "External id": 1406064,"Sequence number": 15109049, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 15028 + } + }, + { + "ph": "s", "id": 17, "pid": 2338710, "tid": 2338710, "ts": 6410531209324.946, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410531209340.178, "dur": 28.451, + "args": { + "External id": 1406065,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410531209340.734, "dur": 27.712, + "args": { + "External id": 1406066,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531209342.446, "dur": 4.920, + "args": { + "External id": 1406067,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531209343.861, "dur": 3.037, + "args": { + "External id": 1406068,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209348.036, "dur": 19.919, + "args": { + "External id": 1406069,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 15033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531209384.250, "dur": 26.947, + "args": { + "External id": 1406070,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531209385.801, "dur": 5.620, + "args": { + "External id": 1406071,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209387.510, "dur": 3.600, + "args": { + "External id": 1406072,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209392.750, "dur": 18.235, + "args": { + "External id": 1406073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209394.481, "dur": 16.054, + "args": { + "External id": 1406074,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531209429.933, "dur": 28.953, + "args": { + "External id": 1406075,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531209431.378, "dur": 7.915, + "args": { + "External id": 1406076,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209435.054, "dur": 3.819, + "args": { + "External id": 1406077,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209439.887, "dur": 18.787, + "args": { + "External id": 1406078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209440.577, "dur": 17.652, + "args": { + "External id": 1406079,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 15043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410531209466.139, "dur": 18.791, + "args": { + "External id": 1406080,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 15044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531209467.963, "dur": 3.170, + "args": { + "External id": 1406081,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209471.732, "dur": 12.918, + "args": { + "External id": 1406082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 15046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209472.690, "dur": 11.500, + "args": { + "External id": 1406083,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410531209492.519, "dur": 24.937, + "args": { + "External id": 1406084,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531209520.500, "dur": 52.770, + "args": { + "External id": 1406085,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531209522.417, "dur": 50.329, + "args": { + "External id": 1406086,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209526.715, "dur": 1.142, + "args": { + "External id": 1406087,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531209529.133, "dur": 26.180, + "args": { + "External id": 1406088,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531209533.184, "dur": 21.913, + "args": { + "External id": 1406089,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 15053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531209535.444, "dur": 2.470, + "args": { + "External id": 1406090,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531209538.683, "dur": 16.072, + "args": { + "External id": 1406091,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 15055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410531209577.259, "dur": 40883.309, + "args": { + "External id": 1406092,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410531209578.855, "dur": 40879.536, + "args": { + "External id": 1406093,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531250480.792, "dur": 13.740, + "args": { + "External id": 1406094,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531250489.858, "dur": 1.904, + "args": { + "External id": 1406095,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531250500.713, "dur": 120.812, + "args": { + "External id": 1406096,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531250502.519, "dur": 7.355, + "args": { + "External id": 1406097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531250505.181, "dur": 3.758, + "args": { + "External id": 1406098,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531250507.445, "dur": 1.193, + "args": { + "External id": 1406099,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531250511.423, "dur": 109.278, + "args": { + "External id": 1406100,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531250515.328, "dur": 104.582, + "args": { + "External id": 1406101,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531250626.072, "dur": 4.483, + "args": { + "External id": 1406102,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531250628.135, "dur": 0.786, + "args": { + "External id": 1406103,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531250640.178, "dur": 3.330, + "args": { + "External id": 1406104,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531250654.486, "dur": 8.003, + "args": { + "External id": 1406105,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531250656.861, "dur": 5.346, + "args": { + "External id": 1406106,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531250805.241, "dur": 208.801, + "args": { + "External id": 1406107,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531250808.172, "dur": 4.896, + "args": { + "External id": 1406108,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531250814.962, "dur": 198.554, + "args": { + "External id": 1406109,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531250816.603, "dur": 0.682, + "args": { + "External id": 1406110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531250818.736, "dur": 29.086, + "args": { + "External id": 1406111,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531250849.672, "dur": 5.430, + "args": { + "External id": 1406112,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531250854.128, "dur": 0.680, + "args": { + "External id": 1406113,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531250856.229, "dur": 28.875, + "args": { + "External id": 1406114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531250857.381, "dur": 1.573, + "args": { + "External id": 1406115,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531250862.821, "dur": 21.987, + "args": { + "External id": 1406116,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531250866.843, "dur": 3.214, + "args": { + "External id": 1406117,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531250886.790, "dur": 23.838, + "args": { + "External id": 1406118,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531250912.675, "dur": 16.100, + "args": { + "External id": 1406119,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531250932.106, "dur": 13.923, + "args": { + "External id": 1406120,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531250947.543, "dur": 12.412, + "args": { + "External id": 1406121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531250961.637, "dur": 24.828, + "args": { + "External id": 1406122,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531250966.218, "dur": 1.661, + "args": { + "External id": 1406123,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531250972.296, "dur": 0.713, + "args": { + "External id": 1406124,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531250988.236, "dur": 12.000, + "args": { + "External id": 1406125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251001.689, "dur": 10.830, + "args": { + "External id": 1406126,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531251021.483, "dur": 2.081, + "args": { + "External id": 1406127,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531251030.668, "dur": 4.111, + "args": { + "External id": 1406128,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251033.163, "dur": 0.426, + "args": { + "External id": 1406129,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531251162.818, "dur": 77.929, + "args": { + "External id": 1406130,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531251247.403, "dur": 10.290, + "args": { + "External id": 1406131,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251253.230, "dur": 1.074, + "args": { + "External id": 1406132,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251259.488, "dur": 27.354, + "args": { + "External id": 1406133,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531251293.249, "dur": 6.885, + "args": { + "External id": 1406134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531251295.050, "dur": 4.301, + "args": { + "External id": 1406135,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251297.349, "dur": 1.716, + "args": { + "External id": 1406136,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531251303.743, "dur": 49.026, + "args": { + "External id": 1406137,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531251307.121, "dur": 44.900, + "args": { + "External id": 1406138,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251374.074, "dur": 16.991, + "args": { + "External id": 1406139,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531251398.588, "dur": 4.062, + "args": { + "External id": 1406140,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251401.102, "dur": 0.585, + "args": { + "External id": 1406141,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531251407.632, "dur": 72.651, + "args": { + "External id": 1406142,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531251408.409, "dur": 22.363, + "args": { + "External id": 1406143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531251411.486, "dur": 18.312, + "args": { + "External id": 1406144,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251412.829, "dur": 16.358, + "args": { + "External id": 1406145,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531251432.155, "dur": 47.618, + "args": { + "External id": 1406146,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531251433.031, "dur": 46.099, + "args": { + "External id": 1406147,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531251486.293, "dur": 4.357, + "args": { + "External id": 1406148,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251488.661, "dur": 0.673, + "args": { + "External id": 1406149,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531251498.320, "dur": 2.371, + "args": { + "External id": 1406150,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531251511.653, "dur": 8.779, + "args": { + "External id": 1406151,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531251513.816, "dur": 6.292, + "args": { + "External id": 1406152,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531251622.588, "dur": 188.369, + "args": { + "External id": 1406153,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531251624.653, "dur": 1.730, + "args": { + "External id": 1406154,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531251627.884, "dur": 182.686, + "args": { + "External id": 1406155,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531251629.698, "dur": 0.384, + "args": { + "External id": 1406156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531251633.930, "dur": 26.068, + "args": { + "External id": 1406157,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531251661.477, "dur": 3.653, + "args": { + "External id": 1406158,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251663.745, "dur": 0.940, + "args": { + "External id": 1406159,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531251665.943, "dur": 24.125, + "args": { + "External id": 1406160,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531251666.923, "dur": 1.431, + "args": { + "External id": 1406161,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531251669.470, "dur": 20.280, + "args": { + "External id": 1406162,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251674.329, "dur": 2.795, + "args": { + "External id": 1406163,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531251691.763, "dur": 23.900, + "args": { + "External id": 1406164,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251717.361, "dur": 12.718, + "args": { + "External id": 1406165,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531251732.850, "dur": 14.899, + "args": { + "External id": 1406166,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251749.139, "dur": 11.584, + "args": { + "External id": 1406167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531251764.792, "dur": 19.522, + "args": { + "External id": 1406168,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251766.637, "dur": 1.763, + "args": { + "External id": 1406169,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251770.628, "dur": 0.550, + "args": { + "External id": 1406170,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251785.833, "dur": 11.230, + "args": { + "External id": 1406171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251798.160, "dur": 11.250, + "args": { + "External id": 1406172,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531251817.650, "dur": 1.842, + "args": { + "External id": 1406173,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531251828.441, "dur": 4.045, + "args": { + "External id": 1406174,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251831.065, "dur": 0.494, + "args": { + "External id": 1406175,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531251906.132, "dur": 55.507, + "args": { + "External id": 1406176,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531251966.533, "dur": 6.244, + "args": { + "External id": 1406177,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531251969.323, "dur": 2.271, + "args": { + "External id": 1406178,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531251974.082, "dur": 28.196, + "args": { + "External id": 1406179,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531252006.784, "dur": 6.807, + "args": { + "External id": 1406180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531252008.127, "dur": 4.704, + "args": { + "External id": 1406181,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252012.032, "dur": 0.612, + "args": { + "External id": 1406182,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531252016.447, "dur": 92.252, + "args": { + "External id": 1406183,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531252017.444, "dur": 90.099, + "args": { + "External id": 1406184,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252115.065, "dur": 19.060, + "args": { + "External id": 1406185,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531252141.764, "dur": 4.558, + "args": { + "External id": 1406186,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252144.372, "dur": 0.855, + "args": { + "External id": 1406187,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531252150.773, "dur": 51.909, + "args": { + "External id": 1406188,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531252154.171, "dur": 4.480, + "args": { + "External id": 1406189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531252155.241, "dur": 2.783, + "args": { + "External id": 1406190,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252156.797, "dur": 1.043, + "args": { + "External id": 1406191,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531252159.405, "dur": 42.880, + "args": { + "External id": 1406192,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531252160.112, "dur": 41.687, + "args": { + "External id": 1406193,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531252213.680, "dur": 8.683, + "args": { + "External id": 1406194,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252220.381, "dur": 0.897, + "args": { + "External id": 1406195,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531252231.924, "dur": 2.007, + "args": { + "External id": 1406196,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531252242.322, "dur": 10.001, + "args": { + "External id": 1406197,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531252244.255, "dur": 7.783, + "args": { + "External id": 1406198,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531252350.134, "dur": 206.350, + "args": { + "External id": 1406199,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531252352.025, "dur": 1.999, + "args": { + "External id": 1406200,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531252355.290, "dur": 200.750, + "args": { + "External id": 1406201,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531252358.814, "dur": 0.371, + "args": { + "External id": 1406202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531252360.694, "dur": 22.394, + "args": { + "External id": 1406203,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531252384.663, "dur": 3.055, + "args": { + "External id": 1406204,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252386.718, "dur": 0.779, + "args": { + "External id": 1406205,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531252388.664, "dur": 22.112, + "args": { + "External id": 1406206,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531252389.690, "dur": 1.329, + "args": { + "External id": 1406207,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531252392.079, "dur": 18.426, + "args": { + "External id": 1406208,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252395.870, "dur": 3.210, + "args": { + "External id": 1406209,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531252412.351, "dur": 41.023, + "args": { + "External id": 1406210,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252455.837, "dur": 13.341, + "args": { + "External id": 1406211,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531252474.217, "dur": 12.910, + "args": { + "External id": 1406212,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252488.664, "dur": 14.664, + "args": { + "External id": 1406213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531252505.545, "dur": 21.780, + "args": { + "External id": 1406214,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252507.985, "dur": 2.103, + "args": { + "External id": 1406215,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252511.985, "dur": 0.637, + "args": { + "External id": 1406216,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252528.925, "dur": 12.676, + "args": { + "External id": 1406217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252544.948, "dur": 10.000, + "args": { + "External id": 1406218,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531252564.296, "dur": 2.336, + "args": { + "External id": 1406219,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531252575.855, "dur": 3.570, + "args": { + "External id": 1406220,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252578.258, "dur": 0.435, + "args": { + "External id": 1406221,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531252652.162, "dur": 64.196, + "args": { + "External id": 1406222,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531252721.657, "dur": 4.621, + "args": { + "External id": 1406223,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252724.540, "dur": 0.523, + "args": { + "External id": 1406224,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252728.030, "dur": 30.926, + "args": { + "External id": 1406225,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531252765.612, "dur": 5.080, + "args": { + "External id": 1406226,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531252767.052, "dur": 2.994, + "args": { + "External id": 1406227,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252768.988, "dur": 0.899, + "args": { + "External id": 1406228,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531252773.414, "dur": 43.033, + "args": { + "External id": 1406229,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531252774.377, "dur": 41.502, + "args": { + "External id": 1406230,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531252820.332, "dur": 15.185, + "args": { + "External id": 1406231,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531252841.454, "dur": 5.538, + "args": { + "External id": 1406232,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252845.612, "dur": 0.538, + "args": { + "External id": 1406233,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531252851.171, "dur": 44.882, + "args": { + "External id": 1406234,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531252851.999, "dur": 3.080, + "args": { + "External id": 1406235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531252852.625, "dur": 1.877, + "args": { + "External id": 1406236,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252853.794, "dur": 0.578, + "args": { + "External id": 1406237,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531252855.779, "dur": 39.866, + "args": { + "External id": 1406238,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531252858.870, "dur": 36.255, + "args": { + "External id": 1406239,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531252900.452, "dur": 4.472, + "args": { + "External id": 1406240,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531252902.070, "dur": 1.824, + "args": { + "External id": 1406241,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531252910.399, "dur": 1.693, + "args": { + "External id": 1406242,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531252920.093, "dur": 6.413, + "args": { + "External id": 1406243,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531252922.047, "dur": 4.189, + "args": { + "External id": 1406244,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531253013.493, "dur": 244.540, + "args": { + "External id": 1406245,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531253015.317, "dur": 3.507, + "args": { + "External id": 1406246,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531253020.306, "dur": 237.257, + "args": { + "External id": 1406247,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531253021.521, "dur": 0.319, + "args": { + "External id": 1406248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531253022.856, "dur": 20.286, + "args": { + "External id": 1406249,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531253044.788, "dur": 2.741, + "args": { + "External id": 1406250,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253046.589, "dur": 0.670, + "args": { + "External id": 1406251,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531253048.316, "dur": 78.248, + "args": { + "External id": 1406252,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531253049.270, "dur": 1.253, + "args": { + "External id": 1406253,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531253101.339, "dur": 24.827, + "args": { + "External id": 1406254,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253107.004, "dur": 3.162, + "args": { + "External id": 1406255,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531253128.186, "dur": 22.562, + "args": { + "External id": 1406256,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253152.357, "dur": 14.356, + "args": { + "External id": 1406257,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531253169.485, "dur": 16.328, + "args": { + "External id": 1406258,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253187.500, "dur": 13.754, + "args": { + "External id": 1406259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531253203.391, "dur": 22.152, + "args": { + "External id": 1406260,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253205.497, "dur": 1.882, + "args": { + "External id": 1406261,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253209.232, "dur": 0.852, + "args": { + "External id": 1406262,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253229.132, "dur": 13.477, + "args": { + "External id": 1406263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253243.820, "dur": 12.650, + "args": { + "External id": 1406264,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531253266.389, "dur": 2.431, + "args": { + "External id": 1406265,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531253277.838, "dur": 4.136, + "args": { + "External id": 1406266,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253280.379, "dur": 0.674, + "args": { + "External id": 1406267,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531253356.482, "dur": 81.562, + "args": { + "External id": 1406268,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531253445.141, "dur": 6.098, + "args": { + "External id": 1406269,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253448.661, "dur": 1.020, + "args": { + "External id": 1406270,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253455.090, "dur": 28.467, + "args": { + "External id": 1406271,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531253489.229, "dur": 5.110, + "args": { + "External id": 1406272,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531253490.979, "dur": 2.635, + "args": { + "External id": 1406273,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253492.574, "dur": 0.828, + "args": { + "External id": 1406274,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531253497.467, "dur": 47.517, + "args": { + "External id": 1406275,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531253498.380, "dur": 46.015, + "args": { + "External id": 1406276,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253549.086, "dur": 21.991, + "args": { + "External id": 1406277,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531253579.858, "dur": 3.574, + "args": { + "External id": 1406278,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253581.937, "dur": 0.681, + "args": { + "External id": 1406279,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531253587.388, "dur": 48.108, + "args": { + "External id": 1406280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531253588.101, "dur": 4.264, + "args": { + "External id": 1406281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531253588.869, "dur": 2.836, + "args": { + "External id": 1406282,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253591.011, "dur": 0.550, + "args": { + "External id": 1406283,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531253595.337, "dur": 39.802, + "args": { + "External id": 1406284,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531253596.010, "dur": 38.606, + "args": { + "External id": 1406285,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531253639.735, "dur": 3.135, + "args": { + "External id": 1406286,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253641.277, "dur": 0.430, + "args": { + "External id": 1406287,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531253648.436, "dur": 1.475, + "args": { + "External id": 1406288,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531253657.850, "dur": 9.938, + "args": { + "External id": 1406289,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531253662.038, "dur": 5.497, + "args": { + "External id": 1406290,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531253761.556, "dur": 179.006, + "args": { + "External id": 1406291,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531253763.876, "dur": 1.938, + "args": { + "External id": 1406292,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531253767.221, "dur": 172.816, + "args": { + "External id": 1406293,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531253769.673, "dur": 0.337, + "args": { + "External id": 1406294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531253771.190, "dur": 19.880, + "args": { + "External id": 1406295,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531253792.786, "dur": 2.751, + "args": { + "External id": 1406296,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253794.436, "dur": 0.845, + "args": { + "External id": 1406297,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531253796.397, "dur": 23.057, + "args": { + "External id": 1406298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531253800.713, "dur": 1.462, + "args": { + "External id": 1406299,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531253803.317, "dur": 15.857, + "args": { + "External id": 1406300,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253805.605, "dur": 2.539, + "args": { + "External id": 1406301,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531253820.861, "dur": 20.607, + "args": { + "External id": 1406302,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253842.952, "dur": 14.229, + "args": { + "External id": 1406303,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531253859.696, "dur": 13.777, + "args": { + "External id": 1406304,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253874.837, "dur": 13.603, + "args": { + "External id": 1406305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531253890.243, "dur": 21.718, + "args": { + "External id": 1406306,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253892.466, "dur": 1.455, + "args": { + "External id": 1406307,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253897.561, "dur": 0.383, + "args": { + "External id": 1406308,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253913.200, "dur": 13.923, + "args": { + "External id": 1406309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531253928.239, "dur": 10.894, + "args": { + "External id": 1406310,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531253947.129, "dur": 1.995, + "args": { + "External id": 1406311,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531253956.637, "dur": 2.880, + "args": { + "External id": 1406312,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531253958.386, "dur": 0.369, + "args": { + "External id": 1406313,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531254024.619, "dur": 90.541, + "args": { + "External id": 1406314,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531254124.669, "dur": 7.737, + "args": { + "External id": 1406315,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254128.147, "dur": 2.759, + "args": { + "External id": 1406316,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254134.073, "dur": 27.015, + "args": { + "External id": 1406317,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531254166.419, "dur": 4.717, + "args": { + "External id": 1406318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531254168.004, "dur": 2.471, + "args": { + "External id": 1406319,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254169.609, "dur": 0.686, + "args": { + "External id": 1406320,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531254176.702, "dur": 46.810, + "args": { + "External id": 1406321,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531254177.582, "dur": 45.151, + "args": { + "External id": 1406322,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254239.704, "dur": 24.464, + "args": { + "External id": 1406323,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531254270.664, "dur": 4.695, + "args": { + "External id": 1406324,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254273.968, "dur": 0.507, + "args": { + "External id": 1406325,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531254279.389, "dur": 46.710, + "args": { + "External id": 1406326,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531254280.283, "dur": 5.137, + "args": { + "External id": 1406327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531254283.262, "dur": 1.578, + "args": { + "External id": 1406328,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254284.188, "dur": 0.476, + "args": { + "External id": 1406329,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531254286.086, "dur": 39.609, + "args": { + "External id": 1406330,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531254286.717, "dur": 38.285, + "args": { + "External id": 1406331,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531254330.930, "dur": 3.466, + "args": { + "External id": 1406332,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254332.760, "dur": 0.416, + "args": { + "External id": 1406333,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531254340.061, "dur": 2.079, + "args": { + "External id": 1406334,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531254352.869, "dur": 8.748, + "args": { + "External id": 1406335,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531254354.875, "dur": 6.418, + "args": { + "External id": 1406336,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531254469.977, "dur": 184.139, + "args": { + "External id": 1406337,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531254472.079, "dur": 2.960, + "args": { + "External id": 1406338,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531254476.629, "dur": 177.032, + "args": { + "External id": 1406339,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531254478.055, "dur": 0.529, + "args": { + "External id": 1406340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531254482.175, "dur": 25.157, + "args": { + "External id": 1406341,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531254508.969, "dur": 3.020, + "args": { + "External id": 1406342,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254510.986, "dur": 0.726, + "args": { + "External id": 1406343,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531254512.742, "dur": 23.210, + "args": { + "External id": 1406344,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531254513.729, "dur": 1.766, + "args": { + "External id": 1406345,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531254516.477, "dur": 19.226, + "args": { + "External id": 1406346,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254520.051, "dur": 2.562, + "args": { + "External id": 1406347,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531254537.346, "dur": 21.171, + "args": { + "External id": 1406348,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254560.142, "dur": 14.107, + "args": { + "External id": 1406349,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531254576.597, "dur": 14.020, + "args": { + "External id": 1406350,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254591.973, "dur": 13.376, + "args": { + "External id": 1406351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531254609.573, "dur": 18.549, + "args": { + "External id": 1406352,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254611.538, "dur": 1.671, + "args": { + "External id": 1406353,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254614.819, "dur": 0.455, + "args": { + "External id": 1406354,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254629.573, "dur": 11.054, + "args": { + "External id": 1406355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254641.616, "dur": 11.088, + "args": { + "External id": 1406356,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531254660.912, "dur": 2.103, + "args": { + "External id": 1406357,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531254671.919, "dur": 3.898, + "args": { + "External id": 1406358,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254674.401, "dur": 0.574, + "args": { + "External id": 1406359,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531254742.223, "dur": 54.961, + "args": { + "External id": 1406360,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531254802.175, "dur": 4.287, + "args": { + "External id": 1406361,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254804.630, "dur": 0.680, + "args": { + "External id": 1406362,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254807.893, "dur": 22.933, + "args": { + "External id": 1406363,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531254835.106, "dur": 7.267, + "args": { + "External id": 1406364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531254836.711, "dur": 4.925, + "args": { + "External id": 1406365,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254840.453, "dur": 1.030, + "args": { + "External id": 1406366,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531254844.794, "dur": 41.688, + "args": { + "External id": 1406367,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531254846.001, "dur": 39.674, + "args": { + "External id": 1406368,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531254890.270, "dur": 13.890, + "args": { + "External id": 1406369,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531254910.152, "dur": 3.265, + "args": { + "External id": 1406370,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254912.118, "dur": 0.466, + "args": { + "External id": 1406371,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531254916.998, "dur": 46.471, + "args": { + "External id": 1406372,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531254920.256, "dur": 3.263, + "args": { + "External id": 1406373,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531254921.132, "dur": 1.829, + "args": { + "External id": 1406374,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254922.446, "dur": 0.404, + "args": { + "External id": 1406375,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531254924.239, "dur": 38.808, + "args": { + "External id": 1406376,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531254924.659, "dur": 37.449, + "args": { + "External id": 1406377,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531254967.853, "dur": 6.120, + "args": { + "External id": 1406378,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531254969.759, "dur": 2.971, + "args": { + "External id": 1406379,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531254981.816, "dur": 1.307, + "args": { + "External id": 1406380,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531254991.266, "dur": 10.051, + "args": { + "External id": 1406381,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531254997.566, "dur": 3.431, + "args": { + "External id": 1406382,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531255124.671, "dur": 190.099, + "args": { + "External id": 1406383,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531255126.952, "dur": 3.179, + "args": { + "External id": 1406384,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531255133.178, "dur": 181.132, + "args": { + "External id": 1406385,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531255136.652, "dur": 0.426, + "args": { + "External id": 1406386,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531255138.095, "dur": 21.900, + "args": { + "External id": 1406387,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531255161.545, "dur": 3.874, + "args": { + "External id": 1406388,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255163.240, "dur": 1.847, + "args": { + "External id": 1406389,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531255166.224, "dur": 22.673, + "args": { + "External id": 1406390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531255167.092, "dur": 1.320, + "args": { + "External id": 1406391,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531255169.393, "dur": 19.223, + "args": { + "External id": 1406392,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255171.823, "dur": 2.796, + "args": { + "External id": 1406393,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531255190.248, "dur": 20.950, + "args": { + "External id": 1406394,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255212.826, "dur": 12.751, + "args": { + "External id": 1406395,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531255230.871, "dur": 14.911, + "args": { + "External id": 1406396,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255247.107, "dur": 14.107, + "args": { + "External id": 1406397,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531255262.943, "dur": 20.437, + "args": { + "External id": 1406398,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255264.780, "dur": 1.719, + "args": { + "External id": 1406399,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255268.030, "dur": 0.667, + "args": { + "External id": 1406400,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255284.770, "dur": 13.349, + "args": { + "External id": 1406401,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255301.455, "dur": 11.855, + "args": { + "External id": 1406402,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531255322.019, "dur": 2.011, + "args": { + "External id": 1406403,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531255332.352, "dur": 3.756, + "args": { + "External id": 1406404,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255334.790, "dur": 0.508, + "args": { + "External id": 1406405,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531255402.137, "dur": 74.840, + "args": { + "External id": 1406406,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531255483.722, "dur": 7.055, + "args": { + "External id": 1406407,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255487.004, "dur": 2.098, + "args": { + "External id": 1406408,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255492.183, "dur": 25.815, + "args": { + "External id": 1406409,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531255525.671, "dur": 5.166, + "args": { + "External id": 1406410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531255527.253, "dur": 2.896, + "args": { + "External id": 1406411,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255529.173, "dur": 0.723, + "args": { + "External id": 1406412,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531255533.863, "dur": 44.034, + "args": { + "External id": 1406413,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531255534.784, "dur": 42.420, + "args": { + "External id": 1406414,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255581.648, "dur": 14.581, + "args": { + "External id": 1406415,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531255602.101, "dur": 5.598, + "args": { + "External id": 1406416,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255606.421, "dur": 0.463, + "args": { + "External id": 1406417,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531255611.453, "dur": 51.071, + "args": { + "External id": 1406418,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531255616.330, "dur": 3.471, + "args": { + "External id": 1406419,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531255617.078, "dur": 2.166, + "args": { + "External id": 1406420,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255618.308, "dur": 0.614, + "args": { + "External id": 1406421,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531255620.313, "dur": 41.887, + "args": { + "External id": 1406422,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531255623.491, "dur": 38.042, + "args": { + "External id": 1406423,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531255666.928, "dur": 3.400, + "args": { + "External id": 1406424,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255668.732, "dur": 0.411, + "args": { + "External id": 1406425,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531255675.598, "dur": 1.432, + "args": { + "External id": 1406426,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531255684.469, "dur": 7.646, + "args": { + "External id": 1406427,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531255686.593, "dur": 5.223, + "args": { + "External id": 1406428,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531255777.745, "dur": 183.704, + "args": { + "External id": 1406429,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531255779.627, "dur": 2.118, + "args": { + "External id": 1406430,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531255783.221, "dur": 177.759, + "args": { + "External id": 1406431,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531255784.451, "dur": 0.325, + "args": { + "External id": 1406432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531255785.913, "dur": 24.425, + "args": { + "External id": 1406433,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531255811.847, "dur": 2.761, + "args": { + "External id": 1406434,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255813.615, "dur": 0.682, + "args": { + "External id": 1406435,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531255815.326, "dur": 24.315, + "args": { + "External id": 1406436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531255816.418, "dur": 1.220, + "args": { + "External id": 1406437,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531255820.883, "dur": 18.502, + "args": { + "External id": 1406438,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255824.511, "dur": 2.154, + "args": { + "External id": 1406439,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531255840.827, "dur": 20.706, + "args": { + "External id": 1406440,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255862.949, "dur": 13.619, + "args": { + "External id": 1406441,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531255878.608, "dur": 17.333, + "args": { + "External id": 1406442,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255897.056, "dur": 13.596, + "args": { + "External id": 1406443,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531255912.298, "dur": 20.405, + "args": { + "External id": 1406444,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255914.253, "dur": 1.783, + "args": { + "External id": 1406445,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255917.726, "dur": 0.438, + "args": { + "External id": 1406446,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255935.935, "dur": 11.829, + "args": { + "External id": 1406447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531255948.638, "dur": 11.339, + "args": { + "External id": 1406448,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531255967.381, "dur": 1.534, + "args": { + "External id": 1406449,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531255976.662, "dur": 3.420, + "args": { + "External id": 1406450,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531255978.853, "dur": 0.425, + "args": { + "External id": 1406451,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531256039.925, "dur": 104.524, + "args": { + "External id": 1406452,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531256152.179, "dur": 6.352, + "args": { + "External id": 1406453,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256155.708, "dur": 1.298, + "args": { + "External id": 1406454,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256161.767, "dur": 26.332, + "args": { + "External id": 1406455,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531256193.591, "dur": 4.726, + "args": { + "External id": 1406456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531256195.115, "dur": 2.492, + "args": { + "External id": 1406457,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256196.731, "dur": 0.675, + "args": { + "External id": 1406458,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531256201.534, "dur": 45.786, + "args": { + "External id": 1406459,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531256202.568, "dur": 44.178, + "args": { + "External id": 1406460,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256251.137, "dur": 14.370, + "args": { + "External id": 1406461,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531256272.793, "dur": 27.362, + "args": { + "External id": 1406462,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531256274.899, "dur": 24.858, + "args": { + "External id": 1406463,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256281.385, "dur": 0.544, + "args": { + "External id": 1406464,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531256327.957, "dur": 30.818, + "args": { + "External id": 1406465,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531256329.846, "dur": 28.722, + "args": { + "External id": 1406466,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 15430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256338.182, "dur": 3.777, + "args": { + "External id": 1406467,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256343.071, "dur": 15.080, + "args": { + "External id": 1406468,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531256371.424, "dur": 8.029, + "args": { + "External id": 1406469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531256376.349, "dur": 2.585, + "args": { + "External id": 1406470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531256380.655, "dur": 1.086, + "args": { + "External id": 1406471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531256381.193, "dur": 0.439, + "args": { + "External id": 1406472,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256439.236, "dur": 31.035, + "args": { + "External id": 1406473,"Sequence number": 15109050, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256472.234, "dur": 12.564, + "args": { + "External id": 1406474,"Sequence number": 15109051, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15438 + } + }, + { + "ph": "s", "id": 16, "pid": 2338710, "tid": 2338710, "ts": 6410531256472.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531256491.231, "dur": 6.640, + "args": { + "External id": 1406475,"Sequence number": 15109052, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 15439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256494.986, "dur": 1.360, + "args": { + "External id": 1406476,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410531256500.226, "dur": 7.977, + "args": { + "External id": 1406477,"Sequence number": 15109052, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 15441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256506.285, "dur": 0.349, + "args": { + "External id": 1406478,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531256509.309, "dur": 1.931, + "args": { + "External id": 1406479,"Sequence number": 15109052, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 15443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256510.433, "dur": 0.246, + "args": { + "External id": 1406480,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 15444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531256515.218, "dur": 5.048, + "args": { + "External id": 1406481,"Sequence number": 15109052, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15445 + } + }, + { + "ph": "s", "id": 15, "pid": 2338710, "tid": 2338710, "ts": 6410531256515.218, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256518.295, "dur": 0.718, + "args": { + "External id": 1406482,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531256523.386, "dur": 5.348, + "args": { + "External id": 1406483,"Sequence number": 15109053, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15447 + } + }, + { + "ph": "s", "id": 14, "pid": 2338710, "tid": 2338710, "ts": 6410531256523.386, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256527.438, "dur": 0.411, + "args": { + "External id": 1406484,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410531256529.633, "dur": 3.953, + "args": { + "External id": 1406485,"Sequence number": 15109054, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 15449 + } + }, + { + "ph": "s", "id": 13, "pid": 2338710, "tid": 2338710, "ts": 6410531256529.633, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256532.342, "dur": 0.437, + "args": { + "External id": 1406486,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531256534.586, "dur": 5.180, + "args": { + "External id": 1406487,"Sequence number": 15109055, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 15451 + } + }, + { + "ph": "s", "id": 12, "pid": 2338710, "tid": 2338710, "ts": 6410531256534.586, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256536.642, "dur": 2.308, + "args": { + "External id": 1406488,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 15452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410531256544.369, "dur": 34.832, + "args": { + "External id": 1406489,"Sequence number": 15109056, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410531256548.093, "dur": 30.903, + "args": { + "External id": 1406490,"Sequence number": 15109056, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531256550.668, "dur": 7.446, + "args": { + "External id": 1406491,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 15455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531256552.939, "dur": 4.520, + "args": { + "External id": 1406492,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256558.967, "dur": 19.663, + "args": { + "External id": 1406493,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 15457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531256605.940, "dur": 3.829, + "args": { + "External id": 1406494,"Sequence number": 15109056, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 15458 + } + }, + { + "ph": "s", "id": 11, "pid": 2338710, "tid": 2338710, "ts": 6410531256605.940, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531256611.915, "dur": 1.032, + "args": { + "External id": 1406495,"Sequence number": 15109057, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531256648.794, "dur": 46653.563, + "args": { + "External id": 1406496,"Sequence number": 15109057, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 15460 + } + }, + { + "ph": "s", "id": 10, "pid": 2338710, "tid": 2338710, "ts": 6410531256648.794, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410531256664.945, "dur": 23.077, + "args": { + "External id": 1406497,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410531256665.498, "dur": 22.335, + "args": { + "External id": 1406498,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531256666.925, "dur": 4.515, + "args": { + "External id": 1406499,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531256668.061, "dur": 2.924, + "args": { + "External id": 1406500,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256672.180, "dur": 15.238, + "args": { + "External id": 1406501,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 15465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531256704.071, "dur": 25.592, + "args": { + "External id": 1406502,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531256705.216, "dur": 5.371, + "args": { + "External id": 1406503,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256706.722, "dur": 3.544, + "args": { + "External id": 1406504,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256711.875, "dur": 17.575, + "args": { + "External id": 1406505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256715.607, "dur": 13.461, + "args": { + "External id": 1406506,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531256733.390, "dur": 17.077, + "args": { + "External id": 1406507,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531256733.869, "dur": 3.991, + "args": { + "External id": 1406508,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256735.095, "dur": 2.539, + "args": { + "External id": 1406509,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256738.423, "dur": 11.850, + "args": { + "External id": 1406510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256739.103, "dur": 10.810, + "args": { + "External id": 1406511,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 15475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410531256756.761, "dur": 19.208, + "args": { + "External id": 1406512,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 15476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531256758.099, "dur": 2.668, + "args": { + "External id": 1406513,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256761.355, "dur": 14.339, + "args": { + "External id": 1406514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 15478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256765.632, "dur": 9.744, + "args": { + "External id": 1406515,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410531256780.389, "dur": 24.009, + "args": { + "External id": 1406516,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531256807.055, "dur": 44.217, + "args": { + "External id": 1406517,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531256808.907, "dur": 41.909, + "args": { + "External id": 1406518,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256813.089, "dur": 0.900, + "args": { + "External id": 1406519,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531256815.258, "dur": 20.423, + "args": { + "External id": 1406520,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531256816.769, "dur": 18.630, + "args": { + "External id": 1406521,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 15485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531256819.971, "dur": 2.042, + "args": { + "External id": 1406522,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531256822.695, "dur": 12.287, + "args": { + "External id": 1406523,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 15487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410531256855.140, "dur": 40664.122, + "args": { + "External id": 1406524,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410531256856.332, "dur": 40661.208, + "args": { + "External id": 1406525,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531297534.409, "dur": 6.900, + "args": { + "External id": 1406526,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531297538.480, "dur": 0.998, + "args": { + "External id": 1406527,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531297546.464, "dur": 107.604, + "args": { + "External id": 1406528,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531297547.711, "dur": 6.290, + "args": { + "External id": 1406529,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531297550.110, "dur": 3.096, + "args": { + "External id": 1406530,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531297551.985, "dur": 0.970, + "args": { + "External id": 1406531,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531297557.721, "dur": 95.618, + "args": { + "External id": 1406532,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531297559.621, "dur": 92.660, + "args": { + "External id": 1406533,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531297658.096, "dur": 4.239, + "args": { + "External id": 1406534,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531297660.470, "dur": 0.558, + "args": { + "External id": 1406535,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531297669.879, "dur": 2.407, + "args": { + "External id": 1406536,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531297682.007, "dur": 9.543, + "args": { + "External id": 1406537,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531297686.653, "dur": 4.581, + "args": { + "External id": 1406538,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531297825.524, "dur": 199.163, + "args": { + "External id": 1406539,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531297829.168, "dur": 2.010, + "args": { + "External id": 1406540,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531297832.778, "dur": 191.365, + "args": { + "External id": 1406541,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531297834.310, "dur": 0.444, + "args": { + "External id": 1406542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531297837.454, "dur": 26.319, + "args": { + "External id": 1406543,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531297865.578, "dur": 3.523, + "args": { + "External id": 1406544,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531297867.982, "dur": 0.810, + "args": { + "External id": 1406545,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531297870.247, "dur": 26.555, + "args": { + "External id": 1406546,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531297873.728, "dur": 2.265, + "args": { + "External id": 1406547,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531297877.423, "dur": 19.096, + "args": { + "External id": 1406548,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531297881.081, "dur": 3.036, + "args": { + "External id": 1406549,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531297898.444, "dur": 21.935, + "args": { + "External id": 1406550,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531297922.707, "dur": 13.679, + "args": { + "External id": 1406551,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531297939.415, "dur": 15.122, + "args": { + "External id": 1406552,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531297955.930, "dur": 12.611, + "args": { + "External id": 1406553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531297970.395, "dur": 22.028, + "args": { + "External id": 1406554,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531297972.525, "dur": 1.784, + "args": { + "External id": 1406555,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531297978.478, "dur": 0.548, + "args": { + "External id": 1406556,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531297994.194, "dur": 14.447, + "args": { + "External id": 1406557,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298010.109, "dur": 12.931, + "args": { + "External id": 1406558,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531298031.690, "dur": 1.996, + "args": { + "External id": 1406559,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531298040.344, "dur": 3.603, + "args": { + "External id": 1406560,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298042.636, "dur": 0.405, + "args": { + "External id": 1406561,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531298159.755, "dur": 74.967, + "args": { + "External id": 1406562,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531298242.352, "dur": 7.494, + "args": { + "External id": 1406563,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298245.648, "dur": 1.067, + "args": { + "External id": 1406564,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298251.580, "dur": 29.570, + "args": { + "External id": 1406565,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531298287.108, "dur": 7.480, + "args": { + "External id": 1406566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531298289.004, "dur": 4.704, + "args": { + "External id": 1406567,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298291.042, "dur": 2.380, + "args": { + "External id": 1406568,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531298300.346, "dur": 46.775, + "args": { + "External id": 1406569,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531298301.451, "dur": 44.886, + "args": { + "External id": 1406570,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298351.666, "dur": 16.621, + "args": { + "External id": 1406571,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531298374.993, "dur": 3.362, + "args": { + "External id": 1406572,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298376.953, "dur": 0.419, + "args": { + "External id": 1406573,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531298382.940, "dur": 65.959, + "args": { + "External id": 1406574,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531298384.038, "dur": 5.905, + "args": { + "External id": 1406575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531298387.164, "dur": 2.130, + "args": { + "External id": 1406576,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298388.584, "dur": 0.556, + "args": { + "External id": 1406577,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531298390.489, "dur": 57.888, + "args": { + "External id": 1406578,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531298391.004, "dur": 56.292, + "args": { + "External id": 1406579,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531298455.010, "dur": 4.225, + "args": { + "External id": 1406580,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298457.270, "dur": 0.534, + "args": { + "External id": 1406581,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531298468.840, "dur": 2.145, + "args": { + "External id": 1406582,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531298480.437, "dur": 7.639, + "args": { + "External id": 1406583,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531298482.410, "dur": 5.334, + "args": { + "External id": 1406584,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531298587.988, "dur": 189.001, + "args": { + "External id": 1406585,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531298590.473, "dur": 2.020, + "args": { + "External id": 1406586,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531298595.446, "dur": 180.996, + "args": { + "External id": 1406587,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531298599.026, "dur": 0.449, + "args": { + "External id": 1406588,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531298600.999, "dur": 23.456, + "args": { + "External id": 1406589,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531298626.036, "dur": 4.386, + "args": { + "External id": 1406590,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298628.270, "dur": 1.867, + "args": { + "External id": 1406591,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531298631.200, "dur": 22.168, + "args": { + "External id": 1406592,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531298632.214, "dur": 1.113, + "args": { + "External id": 1406593,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531298634.462, "dur": 18.561, + "args": { + "External id": 1406594,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298637.310, "dur": 3.031, + "args": { + "External id": 1406595,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531298654.882, "dur": 20.936, + "args": { + "External id": 1406596,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298677.750, "dur": 13.996, + "args": { + "External id": 1406597,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531298696.621, "dur": 13.395, + "args": { + "External id": 1406598,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298711.374, "dur": 11.737, + "args": { + "External id": 1406599,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531298724.924, "dur": 21.835, + "args": { + "External id": 1406600,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298726.829, "dur": 1.770, + "args": { + "External id": 1406601,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298730.403, "dur": 1.352, + "args": { + "External id": 1406602,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298748.332, "dur": 13.507, + "args": { + "External id": 1406603,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298763.122, "dur": 12.224, + "args": { + "External id": 1406604,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531298786.089, "dur": 1.833, + "args": { + "External id": 1406605,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531298796.742, "dur": 3.261, + "args": { + "External id": 1406606,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298798.757, "dur": 0.480, + "args": { + "External id": 1406607,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531298869.257, "dur": 56.087, + "args": { + "External id": 1406608,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531298929.989, "dur": 4.509, + "args": { + "External id": 1406609,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298932.609, "dur": 0.859, + "args": { + "External id": 1406610,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531298936.021, "dur": 25.243, + "args": { + "External id": 1406611,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531298965.682, "dur": 7.591, + "args": { + "External id": 1406612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531298967.223, "dur": 5.302, + "args": { + "External id": 1406613,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531298971.222, "dur": 1.113, + "args": { + "External id": 1406614,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531298976.193, "dur": 42.976, + "args": { + "External id": 1406615,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531298977.127, "dur": 41.289, + "args": { + "External id": 1406616,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299023.005, "dur": 13.728, + "args": { + "External id": 1406617,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531299090.793, "dur": 6.149, + "args": { + "External id": 1406618,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299094.437, "dur": 1.013, + "args": { + "External id": 1406619,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531299105.566, "dur": 54.313, + "args": { + "External id": 1406620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531299106.592, "dur": 4.212, + "args": { + "External id": 1406621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531299107.784, "dur": 2.419, + "args": { + "External id": 1406622,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299109.390, "dur": 0.654, + "args": { + "External id": 1406623,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531299111.473, "dur": 47.927, + "args": { + "External id": 1406624,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531299112.084, "dur": 46.608, + "args": { + "External id": 1406625,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531299165.273, "dur": 3.598, + "args": { + "External id": 1406626,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299167.089, "dur": 0.654, + "args": { + "External id": 1406627,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531299177.158, "dur": 1.648, + "args": { + "External id": 1406628,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531299187.537, "dur": 9.160, + "args": { + "External id": 1406629,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531299189.501, "dur": 6.872, + "args": { + "External id": 1406630,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531299286.929, "dur": 214.588, + "args": { + "External id": 1406631,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531299289.229, "dur": 1.832, + "args": { + "External id": 1406632,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531299292.433, "dur": 208.398, + "args": { + "External id": 1406633,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531299296.198, "dur": 0.495, + "args": { + "External id": 1406634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531299297.889, "dur": 22.943, + "args": { + "External id": 1406635,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531299322.604, "dur": 2.960, + "args": { + "External id": 1406636,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299324.632, "dur": 0.678, + "args": { + "External id": 1406637,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531299326.546, "dur": 21.588, + "args": { + "External id": 1406638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531299327.265, "dur": 1.244, + "args": { + "External id": 1406639,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531299329.580, "dur": 18.205, + "args": { + "External id": 1406640,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299333.361, "dur": 2.705, + "args": { + "External id": 1406641,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531299349.733, "dur": 22.290, + "args": { + "External id": 1406642,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299373.978, "dur": 14.234, + "args": { + "External id": 1406643,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531299392.607, "dur": 15.463, + "args": { + "External id": 1406644,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299409.526, "dur": 30.047, + "args": { + "External id": 1406645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531299442.716, "dur": 25.833, + "args": { + "External id": 1406646,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299444.893, "dur": 2.154, + "args": { + "External id": 1406647,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299449.072, "dur": 0.790, + "args": { + "External id": 1406648,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299470.516, "dur": 13.873, + "args": { + "External id": 1406649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299487.832, "dur": 11.892, + "args": { + "External id": 1406650,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531299509.485, "dur": 2.755, + "args": { + "External id": 1406651,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531299521.214, "dur": 3.679, + "args": { + "External id": 1406652,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299523.656, "dur": 0.352, + "args": { + "External id": 1406653,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531299591.650, "dur": 85.247, + "args": { + "External id": 1406654,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531299681.792, "dur": 5.063, + "args": { + "External id": 1406655,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299684.597, "dur": 1.151, + "args": { + "External id": 1406656,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299688.233, "dur": 27.958, + "args": { + "External id": 1406657,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531299723.420, "dur": 4.816, + "args": { + "External id": 1406658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531299724.797, "dur": 2.720, + "args": { + "External id": 1406659,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299726.646, "dur": 0.683, + "args": { + "External id": 1406660,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531299730.949, "dur": 49.428, + "args": { + "External id": 1406661,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531299731.999, "dur": 47.701, + "args": { + "External id": 1406662,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531299783.942, "dur": 17.122, + "args": { + "External id": 1406663,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531299807.215, "dur": 4.848, + "args": { + "External id": 1406664,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299810.722, "dur": 0.516, + "args": { + "External id": 1406665,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531299816.270, "dur": 54.936, + "args": { + "External id": 1406666,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531299817.126, "dur": 4.392, + "args": { + "External id": 1406667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531299817.860, "dur": 3.090, + "args": { + "External id": 1406668,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299819.029, "dur": 1.697, + "args": { + "External id": 1406669,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531299822.168, "dur": 48.731, + "args": { + "External id": 1406670,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531299830.044, "dur": 40.149, + "args": { + "External id": 1406671,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531299875.100, "dur": 3.451, + "args": { + "External id": 1406672,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531299876.666, "dur": 0.772, + "args": { + "External id": 1406673,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531299883.693, "dur": 1.471, + "args": { + "External id": 1406674,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531299893.510, "dur": 10.128, + "args": { + "External id": 1406675,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531299897.664, "dur": 5.718, + "args": { + "External id": 1406676,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531299988.171, "dur": 235.914, + "args": { + "External id": 1406677,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531299991.185, "dur": 1.757, + "args": { + "External id": 1406678,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531299994.318, "dur": 229.102, + "args": { + "External id": 1406679,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531299995.619, "dur": 0.497, + "args": { + "External id": 1406680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531299997.180, "dur": 21.973, + "args": { + "External id": 1406681,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531300020.748, "dur": 3.713, + "args": { + "External id": 1406682,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300023.504, "dur": 0.767, + "args": { + "External id": 1406683,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531300025.261, "dur": 23.249, + "args": { + "External id": 1406684,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531300028.571, "dur": 1.185, + "args": { + "External id": 1406685,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531300031.041, "dur": 17.237, + "args": { + "External id": 1406686,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300033.223, "dur": 1.938, + "args": { + "External id": 1406687,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531300049.852, "dur": 73.730, + "args": { + "External id": 1406688,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300126.331, "dur": 15.281, + "args": { + "External id": 1406689,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531300144.442, "dur": 12.798, + "args": { + "External id": 1406690,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300158.590, "dur": 12.072, + "args": { + "External id": 1406691,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531300173.094, "dur": 22.717, + "args": { + "External id": 1406692,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300175.076, "dur": 2.221, + "args": { + "External id": 1406693,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300181.556, "dur": 0.777, + "args": { + "External id": 1406694,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300197.216, "dur": 12.770, + "args": { + "External id": 1406695,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300211.206, "dur": 10.925, + "args": { + "External id": 1406696,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531300233.269, "dur": 2.409, + "args": { + "External id": 1406697,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531300245.546, "dur": 3.933, + "args": { + "External id": 1406698,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300248.103, "dur": 0.502, + "args": { + "External id": 1406699,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531300320.298, "dur": 60.602, + "args": { + "External id": 1406700,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531300385.880, "dur": 6.408, + "args": { + "External id": 1406701,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300390.603, "dur": 0.682, + "args": { + "External id": 1406702,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300393.683, "dur": 41.841, + "args": { + "External id": 1406703,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531300441.832, "dur": 6.220, + "args": { + "External id": 1406704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531300443.250, "dur": 4.012, + "args": { + "External id": 1406705,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300445.472, "dur": 1.600, + "args": { + "External id": 1406706,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531300451.538, "dur": 47.191, + "args": { + "External id": 1406707,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531300452.551, "dur": 45.571, + "args": { + "External id": 1406708,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300502.536, "dur": 17.185, + "args": { + "External id": 1406709,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531300528.747, "dur": 3.892, + "args": { + "External id": 1406710,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300530.829, "dur": 0.859, + "args": { + "External id": 1406711,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531300536.816, "dur": 47.603, + "args": { + "External id": 1406712,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531300537.714, "dur": 6.099, + "args": { + "External id": 1406713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531300538.698, "dur": 4.573, + "args": { + "External id": 1406714,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300542.373, "dur": 0.768, + "args": { + "External id": 1406715,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531300544.409, "dur": 39.542, + "args": { + "External id": 1406716,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531300545.179, "dur": 38.241, + "args": { + "External id": 1406717,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531300588.965, "dur": 3.270, + "args": { + "External id": 1406718,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300590.826, "dur": 0.366, + "args": { + "External id": 1406719,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531300597.829, "dur": 1.727, + "args": { + "External id": 1406720,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531300607.503, "dur": 9.295, + "args": { + "External id": 1406721,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531300611.318, "dur": 5.196, + "args": { + "External id": 1406722,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531300700.906, "dur": 174.470, + "args": { + "External id": 1406723,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531300702.886, "dur": 2.139, + "args": { + "External id": 1406724,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531300706.637, "dur": 168.134, + "args": { + "External id": 1406725,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531300708.146, "dur": 0.272, + "args": { + "External id": 1406726,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531300709.780, "dur": 21.392, + "args": { + "External id": 1406727,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531300732.885, "dur": 3.259, + "args": { + "External id": 1406728,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300735.176, "dur": 0.737, + "args": { + "External id": 1406729,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531300736.901, "dur": 24.633, + "args": { + "External id": 1406730,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531300740.077, "dur": 1.816, + "args": { + "External id": 1406731,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531300743.011, "dur": 18.261, + "args": { + "External id": 1406732,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300747.190, "dur": 2.511, + "args": { + "External id": 1406733,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531300763.080, "dur": 20.372, + "args": { + "External id": 1406734,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300785.006, "dur": 12.523, + "args": { + "External id": 1406735,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531300799.951, "dur": 14.106, + "args": { + "External id": 1406736,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300815.443, "dur": 11.168, + "args": { + "External id": 1406737,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531300828.623, "dur": 20.455, + "args": { + "External id": 1406738,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300830.506, "dur": 1.571, + "args": { + "External id": 1406739,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300835.782, "dur": 0.507, + "args": { + "External id": 1406740,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300850.523, "dur": 11.368, + "args": { + "External id": 1406741,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531300863.110, "dur": 10.858, + "args": { + "External id": 1406742,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531300881.655, "dur": 1.720, + "args": { + "External id": 1406743,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531300891.646, "dur": 3.900, + "args": { + "External id": 1406744,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531300894.024, "dur": 0.641, + "args": { + "External id": 1406745,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531300957.756, "dur": 52.575, + "args": { + "External id": 1406746,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531301017.616, "dur": 4.672, + "args": { + "External id": 1406747,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301020.296, "dur": 0.887, + "args": { + "External id": 1406748,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301023.733, "dur": 24.704, + "args": { + "External id": 1406749,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531301092.071, "dur": 6.136, + "args": { + "External id": 1406750,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531301093.614, "dur": 3.608, + "args": { + "External id": 1406751,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301095.691, "dur": 1.172, + "args": { + "External id": 1406752,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531301103.960, "dur": 51.630, + "args": { + "External id": 1406753,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531301105.445, "dur": 49.358, + "args": { + "External id": 1406754,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301159.646, "dur": 18.434, + "args": { + "External id": 1406755,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531301184.933, "dur": 3.751, + "args": { + "External id": 1406756,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301187.111, "dur": 0.518, + "args": { + "External id": 1406757,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531301192.705, "dur": 49.693, + "args": { + "External id": 1406758,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531301193.579, "dur": 6.672, + "args": { + "External id": 1406759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531301196.664, "dur": 2.983, + "args": { + "External id": 1406760,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301197.757, "dur": 1.684, + "args": { + "External id": 1406761,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531301201.057, "dur": 40.903, + "args": { + "External id": 1406762,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531301201.840, "dur": 39.536, + "args": { + "External id": 1406763,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531301246.763, "dur": 3.438, + "args": { + "External id": 1406764,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301248.609, "dur": 0.431, + "args": { + "External id": 1406765,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531301258.326, "dur": 1.844, + "args": { + "External id": 1406766,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531301268.806, "dur": 8.342, + "args": { + "External id": 1406767,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531301271.018, "dur": 5.916, + "args": { + "External id": 1406768,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531301368.628, "dur": 193.177, + "args": { + "External id": 1406769,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531301371.209, "dur": 2.098, + "args": { + "External id": 1406770,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531301374.589, "dur": 186.747, + "args": { + "External id": 1406771,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531301378.260, "dur": 0.547, + "args": { + "External id": 1406772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531301381.365, "dur": 21.075, + "args": { + "External id": 1406773,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531301403.962, "dur": 2.711, + "args": { + "External id": 1406774,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301405.907, "dur": 0.507, + "args": { + "External id": 1406775,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531301407.454, "dur": 38.209, + "args": { + "External id": 1406776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531301408.414, "dur": 2.432, + "args": { + "External id": 1406777,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531301411.824, "dur": 33.538, + "args": { + "External id": 1406778,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301414.229, "dur": 17.954, + "args": { + "External id": 1406779,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531301447.553, "dur": 20.102, + "args": { + "External id": 1406780,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301468.970, "dur": 13.292, + "args": { + "External id": 1406781,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531301486.966, "dur": 13.087, + "args": { + "External id": 1406782,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301501.618, "dur": 12.204, + "args": { + "External id": 1406783,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531301516.211, "dur": 18.903, + "args": { + "External id": 1406784,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301518.238, "dur": 1.533, + "args": { + "External id": 1406785,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301521.601, "dur": 0.694, + "args": { + "External id": 1406786,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301536.360, "dur": 11.714, + "args": { + "External id": 1406787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301549.283, "dur": 10.882, + "args": { + "External id": 1406788,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531301571.723, "dur": 2.089, + "args": { + "External id": 1406789,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531301582.501, "dur": 3.526, + "args": { + "External id": 1406790,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301584.709, "dur": 0.400, + "args": { + "External id": 1406791,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531301652.711, "dur": 58.741, + "args": { + "External id": 1406792,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531301716.517, "dur": 4.711, + "args": { + "External id": 1406793,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301719.413, "dur": 0.823, + "args": { + "External id": 1406794,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301722.574, "dur": 26.387, + "args": { + "External id": 1406795,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531301753.226, "dur": 8.318, + "args": { + "External id": 1406796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531301754.868, "dur": 5.968, + "args": { + "External id": 1406797,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301758.509, "dur": 2.126, + "args": { + "External id": 1406798,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531301764.364, "dur": 42.433, + "args": { + "External id": 1406799,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531301765.385, "dur": 40.756, + "args": { + "External id": 1406800,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531301810.660, "dur": 15.295, + "args": { + "External id": 1406801,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531301831.345, "dur": 2.937, + "args": { + "External id": 1406802,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301832.974, "dur": 0.436, + "args": { + "External id": 1406803,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531301840.100, "dur": 43.721, + "args": { + "External id": 1406804,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531301841.075, "dur": 3.237, + "args": { + "External id": 1406805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531301841.582, "dur": 2.195, + "args": { + "External id": 1406806,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301842.999, "dur": 0.632, + "args": { + "External id": 1406807,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531301844.908, "dur": 38.557, + "args": { + "External id": 1406808,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531301845.948, "dur": 36.814, + "args": { + "External id": 1406809,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531301888.244, "dur": 4.703, + "args": { + "External id": 1406810,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531301890.209, "dur": 1.745, + "args": { + "External id": 1406811,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531301900.540, "dur": 1.558, + "args": { + "External id": 1406812,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531301909.552, "dur": 6.050, + "args": { + "External id": 1406813,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531301911.384, "dur": 3.978, + "args": { + "External id": 1406814,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531301993.478, "dur": 234.420, + "args": { + "External id": 1406815,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531301995.513, "dur": 2.349, + "args": { + "External id": 1406816,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531302000.550, "dur": 226.813, + "args": { + "External id": 1406817,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531302004.134, "dur": 0.250, + "args": { + "External id": 1406818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531302005.469, "dur": 20.226, + "args": { + "External id": 1406819,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531302027.255, "dur": 4.120, + "args": { + "External id": 1406820,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302029.270, "dur": 1.844, + "args": { + "External id": 1406821,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531302032.331, "dur": 20.984, + "args": { + "External id": 1406822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531302033.570, "dur": 1.015, + "args": { + "External id": 1406823,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531302035.567, "dur": 17.478, + "args": { + "External id": 1406824,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302037.937, "dur": 2.446, + "args": { + "External id": 1406825,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531302054.544, "dur": 74.117, + "args": { + "External id": 1406826,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302131.150, "dur": 13.564, + "args": { + "External id": 1406827,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531302150.098, "dur": 14.117, + "args": { + "External id": 1406828,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302165.618, "dur": 11.472, + "args": { + "External id": 1406829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531302179.629, "dur": 20.746, + "args": { + "External id": 1406830,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302181.914, "dur": 2.229, + "args": { + "External id": 1406831,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302185.922, "dur": 1.861, + "args": { + "External id": 1406832,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302201.856, "dur": 11.169, + "args": { + "External id": 1406833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302216.351, "dur": 10.131, + "args": { + "External id": 1406834,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531302236.202, "dur": 2.331, + "args": { + "External id": 1406835,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531302247.161, "dur": 3.748, + "args": { + "External id": 1406836,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302249.584, "dur": 0.385, + "args": { + "External id": 1406837,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531302318.344, "dur": 58.714, + "args": { + "External id": 1406838,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531302381.868, "dur": 4.814, + "args": { + "External id": 1406839,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302384.716, "dur": 0.826, + "args": { + "External id": 1406840,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302388.257, "dur": 26.170, + "args": { + "External id": 1406841,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531302436.805, "dur": 5.932, + "args": { + "External id": 1406842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531302438.589, "dur": 3.289, + "args": { + "External id": 1406843,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302440.289, "dur": 1.396, + "args": { + "External id": 1406844,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531302446.258, "dur": 46.664, + "args": { + "External id": 1406845,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531302447.480, "dur": 44.689, + "args": { + "External id": 1406846,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302496.671, "dur": 17.976, + "args": { + "External id": 1406847,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531302521.071, "dur": 5.839, + "args": { + "External id": 1406848,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302525.431, "dur": 0.627, + "args": { + "External id": 1406849,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531302531.138, "dur": 47.679, + "args": { + "External id": 1406850,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531302531.896, "dur": 3.489, + "args": { + "External id": 1406851,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531302532.815, "dur": 2.006, + "args": { + "External id": 1406852,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302534.216, "dur": 0.456, + "args": { + "External id": 1406853,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531302536.070, "dur": 42.365, + "args": { + "External id": 1406854,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531302538.980, "dur": 38.696, + "args": { + "External id": 1406855,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531302582.667, "dur": 3.754, + "args": { + "External id": 1406856,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302584.498, "dur": 0.745, + "args": { + "External id": 1406857,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531302592.027, "dur": 1.447, + "args": { + "External id": 1406858,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531302601.216, "dur": 9.375, + "args": { + "External id": 1406859,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531302605.545, "dur": 4.783, + "args": { + "External id": 1406860,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531302710.723, "dur": 178.291, + "args": { + "External id": 1406861,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531302713.956, "dur": 3.989, + "args": { + "External id": 1406862,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531302719.583, "dur": 169.059, + "args": { + "External id": 1406863,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531302720.909, "dur": 0.513, + "args": { + "External id": 1406864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531302722.549, "dur": 20.376, + "args": { + "External id": 1406865,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531302744.369, "dur": 3.981, + "args": { + "External id": 1406866,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302747.306, "dur": 0.809, + "args": { + "External id": 1406867,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531302751.237, "dur": 19.084, + "args": { + "External id": 1406868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531302752.325, "dur": 1.158, + "args": { + "External id": 1406869,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531302754.365, "dur": 15.709, + "args": { + "External id": 1406870,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302756.768, "dur": 2.169, + "args": { + "External id": 1406871,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531302771.554, "dur": 19.122, + "args": { + "External id": 1406872,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302792.177, "dur": 12.973, + "args": { + "External id": 1406873,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531302807.401, "dur": 13.210, + "args": { + "External id": 1406874,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302821.926, "dur": 14.188, + "args": { + "External id": 1406875,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531302837.874, "dur": 22.723, + "args": { + "External id": 1406876,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302840.518, "dur": 1.555, + "args": { + "External id": 1406877,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302845.689, "dur": 0.762, + "args": { + "External id": 1406878,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302862.019, "dur": 13.590, + "args": { + "External id": 1406879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531302876.577, "dur": 11.180, + "args": { + "External id": 1406880,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531302895.254, "dur": 1.640, + "args": { + "External id": 1406881,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531302904.916, "dur": 3.438, + "args": { + "External id": 1406882,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531302907.081, "dur": 0.507, + "args": { + "External id": 1406883,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531302971.364, "dur": 49.906, + "args": { + "External id": 1406884,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531303025.916, "dur": 6.194, + "args": { + "External id": 1406885,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303030.473, "dur": 0.673, + "args": { + "External id": 1406886,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303033.454, "dur": 72.864, + "args": { + "External id": 1406887,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531303114.004, "dur": 5.894, + "args": { + "External id": 1406888,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531303115.604, "dur": 3.441, + "args": { + "External id": 1406889,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303117.434, "dur": 1.449, + "args": { + "External id": 1406890,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531303122.828, "dur": 52.127, + "args": { + "External id": 1406891,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531303126.317, "dur": 48.139, + "args": { + "External id": 1406892,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303178.785, "dur": 17.592, + "args": { + "External id": 1406893,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531303200.791, "dur": 24.113, + "args": { + "External id": 1406894,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531303202.985, "dur": 21.548, + "args": { + "External id": 1406895,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303207.697, "dur": 0.592, + "args": { + "External id": 1406896,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531303230.443, "dur": 28.593, + "args": { + "External id": 1406897,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531303232.288, "dur": 26.517, + "args": { + "External id": 1406898,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 15862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303236.771, "dur": 3.293, + "args": { + "External id": 1406899,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303241.457, "dur": 16.864, + "args": { + "External id": 1406900,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531303272.044, "dur": 4.591, + "args": { + "External id": 1406901,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531303273.738, "dur": 2.607, + "args": { + "External id": 1406902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531303277.597, "dur": 0.824, + "args": { + "External id": 1406903,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531303277.925, "dur": 0.416, + "args": { + "External id": 1406904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303320.682, "dur": 23.200, + "args": { + "External id": 1406905,"Sequence number": 15109058, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303347.990, "dur": 14.397, + "args": { + "External id": 1406906,"Sequence number": 15109059, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15870 + } + }, + { + "ph": "s", "id": 9, "pid": 2338710, "tid": 2338710, "ts": 6410531303347.990, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531303368.639, "dur": 6.118, + "args": { + "External id": 1406907,"Sequence number": 15109060, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 15871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303372.061, "dur": 1.277, + "args": { + "External id": 1406908,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410531303377.361, "dur": 5.973, + "args": { + "External id": 1406909,"Sequence number": 15109060, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "3"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 15873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303381.436, "dur": 0.631, + "args": { + "External id": 1406910,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531303384.723, "dur": 4.727, + "args": { + "External id": 1406911,"Sequence number": 15109060, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 15875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303388.600, "dur": 0.277, + "args": { + "External id": 1406912,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 15876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531303393.215, "dur": 4.979, + "args": { + "External id": 1406913,"Sequence number": 15109060, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15877 + } + }, + { + "ph": "s", "id": 8, "pid": 2338710, "tid": 2338710, "ts": 6410531303393.215, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303396.194, "dur": 0.696, + "args": { + "External id": 1406914,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531303399.096, "dur": 4.434, + "args": { + "External id": 1406915,"Sequence number": 15109061, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15879 + } + }, + { + "ph": "s", "id": 7, "pid": 2338710, "tid": 2338710, "ts": 6410531303399.096, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303402.417, "dur": 0.274, + "args": { + "External id": 1406916,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410531303404.657, "dur": 27.895, + "args": { + "External id": 1406917,"Sequence number": 15109062, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 15881 + } + }, + { + "ph": "s", "id": 6, "pid": 2338710, "tid": 2338710, "ts": 6410531303404.657, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303429.487, "dur": 0.996, + "args": { + "External id": 1406918,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531303434.513, "dur": 5.109, + "args": { + "External id": 1406919,"Sequence number": 15109063, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 15883 + } + }, + { + "ph": "s", "id": 5, "pid": 2338710, "tid": 2338710, "ts": 6410531303434.513, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303437.150, "dur": 1.430, + "args": { + "External id": 1406920,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 15884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410531303444.898, "dur": 38.996, + "args": { + "External id": 1406921,"Sequence number": 15109064, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410531303446.393, "dur": 37.240, + "args": { + "External id": 1406922,"Sequence number": 15109064, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531303449.264, "dur": 9.101, + "args": { + "External id": 1406923,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 15887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531303451.751, "dur": 5.944, + "args": { + "External id": 1406924,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303459.459, "dur": 23.794, + "args": { + "External id": 1406925,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 15889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531303512.688, "dur": 4.197, + "args": { + "External id": 1406926,"Sequence number": 15109064, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 15890 + } + }, + { + "ph": "s", "id": 4, "pid": 2338710, "tid": 2338710, "ts": 6410531303512.688, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531303519.098, "dur": 0.959, + "args": { + "External id": 1406927,"Sequence number": 15109065, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410531303552.345, "dur": 47012.032, + "args": { + "External id": 1406928,"Sequence number": 15109065, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 15892 + } + }, + { + "ph": "s", "id": 3, "pid": 2338710, "tid": 2338710, "ts": 6410531303552.345, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410531303567.618, "dur": 30.400, + "args": { + "External id": 1406929,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410531303568.357, "dur": 29.405, + "args": { + "External id": 1406930,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531303569.630, "dur": 8.917, + "args": { + "External id": 1406931,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531303573.367, "dur": 4.713, + "args": { + "External id": 1406932,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303579.458, "dur": 17.913, + "args": { + "External id": 1406933,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 15897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531303614.391, "dur": 25.920, + "args": { + "External id": 1406934,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531303615.438, "dur": 5.967, + "args": { + "External id": 1406935,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303616.997, "dur": 4.144, + "args": { + "External id": 1406936,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303622.779, "dur": 17.310, + "args": { + "External id": 1406937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303624.458, "dur": 15.244, + "args": { + "External id": 1406938,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531303648.489, "dur": 22.421, + "args": { + "External id": 1406939,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531303649.058, "dur": 4.780, + "args": { + "External id": 1406940,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303651.256, "dur": 2.322, + "args": { + "External id": 1406941,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303656.718, "dur": 13.994, + "args": { + "External id": 1406942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303657.378, "dur": 12.963, + "args": { + "External id": 1406943,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 15907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410531303676.997, "dur": 19.781, + "args": { + "External id": 1406944,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 15908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531303678.494, "dur": 3.855, + "args": { + "External id": 1406945,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303682.959, "dur": 13.542, + "args": { + "External id": 1406946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 15910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303683.671, "dur": 12.487, + "args": { + "External id": 1406947,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410531303701.258, "dur": 23.824, + "args": { + "External id": 1406948,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531303727.581, "dur": 51.017, + "args": { + "External id": 1406949,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531303731.580, "dur": 46.617, + "args": { + "External id": 1406950,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303735.785, "dur": 0.862, + "args": { + "External id": 1406951,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531303737.940, "dur": 24.061, + "args": { + "External id": 1406952,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531303739.294, "dur": 22.489, + "args": { + "External id": 1406953,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 15917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531303742.444, "dur": 2.865, + "args": { + "External id": 1406954,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531303746.298, "dur": 14.968, + "args": { + "External id": 1406955,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 15919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410531303782.502, "dur": 40738.105, + "args": { + "External id": 1406956,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410531303783.784, "dur": 40734.941, + "args": { + "External id": 1406957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531344537.933, "dur": 9.918, + "args": { + "External id": 1406958,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531344544.147, "dur": 1.333, + "args": { + "External id": 1406959,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531344556.135, "dur": 113.736, + "args": { + "External id": 1406960,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531344557.917, "dur": 7.079, + "args": { + "External id": 1406961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531344560.598, "dur": 3.534, + "args": { + "External id": 1406962,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531344562.601, "dur": 1.237, + "args": { + "External id": 1406963,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531344566.461, "dur": 102.615, + "args": { + "External id": 1406964,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531344568.641, "dur": 99.371, + "args": { + "External id": 1406965,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531344673.747, "dur": 4.579, + "args": { + "External id": 1406966,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531344676.214, "dur": 0.767, + "args": { + "External id": 1406967,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531344689.143, "dur": 2.671, + "args": { + "External id": 1406968,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531344703.710, "dur": 7.867, + "args": { + "External id": 1406969,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531344706.247, "dur": 5.005, + "args": { + "External id": 1406970,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531344853.223, "dur": 303.089, + "args": { + "External id": 1406971,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531344856.738, "dur": 2.426, + "args": { + "External id": 1406972,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531344863.568, "dur": 292.110, + "args": { + "External id": 1406973,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531344866.782, "dur": 0.451, + "args": { + "External id": 1406974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531344868.822, "dur": 31.249, + "args": { + "External id": 1406975,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531344901.830, "dur": 31.818, + "args": { + "External id": 1406976,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531344931.096, "dur": 2.175, + "args": { + "External id": 1406977,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531344934.719, "dur": 34.820, + "args": { + "External id": 1406978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531344935.717, "dur": 10.452, + "args": { + "External id": 1406979,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531344947.735, "dur": 21.523, + "args": { + "External id": 1406980,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531344951.516, "dur": 3.104, + "args": { + "External id": 1406981,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531344973.422, "dur": 24.663, + "args": { + "External id": 1406982,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531344999.991, "dur": 16.743, + "args": { + "External id": 1406983,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531345019.926, "dur": 16.180, + "args": { + "External id": 1406984,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345037.591, "dur": 14.639, + "args": { + "External id": 1406985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531345099.849, "dur": 24.847, + "args": { + "External id": 1406986,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345102.674, "dur": 2.572, + "args": { + "External id": 1406987,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345107.402, "dur": 0.771, + "args": { + "External id": 1406988,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345128.699, "dur": 12.260, + "args": { + "External id": 1406989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345142.425, "dur": 11.926, + "args": { + "External id": 1406990,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531345166.702, "dur": 2.800, + "args": { + "External id": 1406991,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531345177.745, "dur": 4.075, + "args": { + "External id": 1406992,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345180.183, "dur": 0.512, + "args": { + "External id": 1406993,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531345273.534, "dur": 79.966, + "args": { + "External id": 1406994,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531345358.999, "dur": 6.561, + "args": { + "External id": 1406995,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345361.388, "dur": 1.644, + "args": { + "External id": 1406996,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345369.619, "dur": 28.913, + "args": { + "External id": 1406997,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531345404.398, "dur": 5.889, + "args": { + "External id": 1406998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531345406.258, "dur": 3.231, + "args": { + "External id": 1406999,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345408.233, "dur": 0.893, + "args": { + "External id": 1407000,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531345413.652, "dur": 69.608, + "args": { + "External id": 1407001,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531345429.514, "dur": 52.766, + "args": { + "External id": 1407002,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345488.391, "dur": 19.045, + "args": { + "External id": 1407003,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531345517.267, "dur": 4.356, + "args": { + "External id": 1407004,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345519.894, "dur": 0.599, + "args": { + "External id": 1407005,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531345526.060, "dur": 50.647, + "args": { + "External id": 1407006,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531345527.072, "dur": 3.268, + "args": { + "External id": 1407007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531345527.907, "dur": 1.833, + "args": { + "External id": 1407008,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345528.969, "dur": 0.611, + "args": { + "External id": 1407009,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531345533.198, "dur": 43.029, + "args": { + "External id": 1407010,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531345533.896, "dur": 41.731, + "args": { + "External id": 1407011,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531345581.278, "dur": 3.505, + "args": { + "External id": 1407012,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345583.175, "dur": 0.344, + "args": { + "External id": 1407013,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531345591.087, "dur": 1.932, + "args": { + "External id": 1407014,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531345602.114, "dur": 9.612, + "args": { + "External id": 1407015,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531345606.502, "dur": 4.965, + "args": { + "External id": 1407016,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531345714.120, "dur": 198.394, + "args": { + "External id": 1407017,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531345716.354, "dur": 3.043, + "args": { + "External id": 1407018,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531345721.055, "dur": 190.934, + "args": { + "External id": 1407019,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531345722.356, "dur": 0.361, + "args": { + "External id": 1407020,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531345723.880, "dur": 22.607, + "args": { + "External id": 1407021,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531345748.477, "dur": 4.730, + "args": { + "External id": 1407022,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345752.456, "dur": 0.491, + "args": { + "External id": 1407023,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531345756.692, "dur": 22.123, + "args": { + "External id": 1407024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531345757.629, "dur": 1.239, + "args": { + "External id": 1407025,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531345760.264, "dur": 18.185, + "args": { + "External id": 1407026,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345762.758, "dur": 2.469, + "args": { + "External id": 1407027,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531345780.548, "dur": 24.669, + "args": { + "External id": 1407028,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345807.167, "dur": 14.379, + "args": { + "External id": 1407029,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531345824.061, "dur": 14.940, + "args": { + "External id": 1407030,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345840.403, "dur": 14.706, + "args": { + "External id": 1407031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531345857.022, "dur": 24.145, + "args": { + "External id": 1407032,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345860.054, "dur": 1.631, + "args": { + "External id": 1407033,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345865.535, "dur": 0.526, + "args": { + "External id": 1407034,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345882.800, "dur": 14.017, + "args": { + "External id": 1407035,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531345898.058, "dur": 12.746, + "args": { + "External id": 1407036,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531345919.837, "dur": 2.037, + "args": { + "External id": 1407037,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531345931.001, "dur": 3.473, + "args": { + "External id": 1407038,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531345933.184, "dur": 0.363, + "args": { + "External id": 1407039,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531346004.878, "dur": 103.083, + "args": { + "External id": 1407040,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531346115.165, "dur": 8.938, + "args": { + "External id": 1407041,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346121.578, "dur": 0.960, + "args": { + "External id": 1407042,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346125.518, "dur": 32.074, + "args": { + "External id": 1407043,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531346163.101, "dur": 5.490, + "args": { + "External id": 1407044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531346164.645, "dur": 3.285, + "args": { + "External id": 1407045,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346166.506, "dur": 1.182, + "args": { + "External id": 1407046,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531346183.685, "dur": 53.196, + "args": { + "External id": 1407047,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531346187.212, "dur": 49.004, + "args": { + "External id": 1407048,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346241.134, "dur": 17.242, + "args": { + "External id": 1407049,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531346264.894, "dur": 4.137, + "args": { + "External id": 1407050,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346267.401, "dur": 0.540, + "args": { + "External id": 1407051,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531346273.268, "dur": 49.354, + "args": { + "External id": 1407052,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531346274.057, "dur": 5.415, + "args": { + "External id": 1407053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531346274.862, "dur": 4.126, + "args": { + "External id": 1407054,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346278.308, "dur": 0.537, + "args": { + "External id": 1407055,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531346280.151, "dur": 42.074, + "args": { + "External id": 1407056,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531346280.795, "dur": 40.773, + "args": { + "External id": 1407057,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531346326.942, "dur": 3.963, + "args": { + "External id": 1407058,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346328.871, "dur": 0.787, + "args": { + "External id": 1407059,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531346337.069, "dur": 1.740, + "args": { + "External id": 1407060,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531346346.869, "dur": 11.823, + "args": { + "External id": 1407061,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531346351.606, "dur": 6.759, + "args": { + "External id": 1407062,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531346477.211, "dur": 242.814, + "args": { + "External id": 1407063,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531346479.569, "dur": 2.755, + "args": { + "External id": 1407064,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531346483.929, "dur": 235.591, + "args": { + "External id": 1407065,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531346485.876, "dur": 0.348, + "args": { + "External id": 1407066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531346487.561, "dur": 27.893, + "args": { + "External id": 1407067,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531346517.256, "dur": 2.953, + "args": { + "External id": 1407068,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346519.160, "dur": 0.715, + "args": { + "External id": 1407069,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531346523.229, "dur": 24.953, + "args": { + "External id": 1407070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531346524.461, "dur": 1.397, + "args": { + "External id": 1407071,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531346526.951, "dur": 20.929, + "args": { + "External id": 1407072,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346530.614, "dur": 2.731, + "args": { + "External id": 1407073,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531346549.729, "dur": 21.980, + "args": { + "External id": 1407074,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346573.230, "dur": 15.146, + "args": { + "External id": 1407075,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531346591.101, "dur": 13.220, + "args": { + "External id": 1407076,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346605.742, "dur": 11.906, + "args": { + "External id": 1407077,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531346619.714, "dur": 24.676, + "args": { + "External id": 1407078,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346624.181, "dur": 1.657, + "args": { + "External id": 1407079,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346627.664, "dur": 0.391, + "args": { + "External id": 1407080,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346645.807, "dur": 31.073, + "args": { + "External id": 1407081,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346677.999, "dur": 40.622, + "args": { + "External id": 1407082,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531346727.630, "dur": 2.590, + "args": { + "External id": 1407083,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531346739.196, "dur": 3.301, + "args": { + "External id": 1407084,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346741.201, "dur": 0.395, + "args": { + "External id": 1407085,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531346819.709, "dur": 58.963, + "args": { + "External id": 1407086,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531346883.425, "dur": 4.456, + "args": { + "External id": 1407087,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346885.941, "dur": 0.765, + "args": { + "External id": 1407088,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346889.116, "dur": 25.028, + "args": { + "External id": 1407089,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531346918.848, "dur": 7.197, + "args": { + "External id": 1407090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531346920.158, "dur": 5.244, + "args": { + "External id": 1407091,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531346924.376, "dur": 0.824, + "args": { + "External id": 1407092,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531346928.506, "dur": 41.964, + "args": { + "External id": 1407093,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531346929.829, "dur": 40.127, + "args": { + "External id": 1407094,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531346974.101, "dur": 16.296, + "args": { + "External id": 1407095,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531346996.103, "dur": 8.253, + "args": { + "External id": 1407096,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347002.832, "dur": 0.584, + "args": { + "External id": 1407097,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531347008.290, "dur": 86.380, + "args": { + "External id": 1407098,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531347011.184, "dur": 4.306, + "args": { + "External id": 1407099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531347012.072, "dur": 2.885, + "args": { + "External id": 1407100,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347013.063, "dur": 1.627, + "args": { + "External id": 1407101,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531347016.326, "dur": 77.724, + "args": { + "External id": 1407102,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531347017.199, "dur": 75.646, + "args": { + "External id": 1407103,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531347101.458, "dur": 5.054, + "args": { + "External id": 1407104,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347104.154, "dur": 0.900, + "args": { + "External id": 1407105,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531347114.822, "dur": 1.626, + "args": { + "External id": 1407106,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531347124.688, "dur": 8.929, + "args": { + "External id": 1407107,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531347126.790, "dur": 6.588, + "args": { + "External id": 1407108,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531347227.654, "dur": 181.569, + "args": { + "External id": 1407109,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531347230.383, "dur": 2.019, + "args": { + "External id": 1407110,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531347236.092, "dur": 172.607, + "args": { + "External id": 1407111,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531347237.500, "dur": 0.388, + "args": { + "External id": 1407112,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531347240.203, "dur": 22.703, + "args": { + "External id": 1407113,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531347264.950, "dur": 2.945, + "args": { + "External id": 1407114,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347267.005, "dur": 0.629, + "args": { + "External id": 1407115,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531347268.779, "dur": 20.735, + "args": { + "External id": 1407116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531347269.749, "dur": 2.225, + "args": { + "External id": 1407117,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531347273.025, "dur": 16.165, + "args": { + "External id": 1407118,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347275.580, "dur": 2.464, + "args": { + "External id": 1407119,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531347290.990, "dur": 19.783, + "args": { + "External id": 1407120,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347312.330, "dur": 12.487, + "args": { + "External id": 1407121,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531347329.234, "dur": 13.460, + "args": { + "External id": 1407122,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347344.105, "dur": 12.002, + "args": { + "External id": 1407123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531347357.628, "dur": 20.036, + "args": { + "External id": 1407124,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347359.570, "dur": 1.753, + "args": { + "External id": 1407125,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347363.066, "dur": 0.404, + "args": { + "External id": 1407126,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347378.948, "dur": 13.339, + "args": { + "External id": 1407127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347395.639, "dur": 11.806, + "args": { + "External id": 1407128,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531347430.896, "dur": 2.525, + "args": { + "External id": 1407129,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531347443.474, "dur": 3.915, + "args": { + "External id": 1407130,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347445.932, "dur": 0.627, + "args": { + "External id": 1407131,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531347522.154, "dur": 64.360, + "args": { + "External id": 1407132,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531347591.507, "dur": 4.768, + "args": { + "External id": 1407133,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347594.144, "dur": 0.817, + "args": { + "External id": 1407134,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347597.705, "dur": 25.285, + "args": { + "External id": 1407135,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531347627.790, "dur": 8.721, + "args": { + "External id": 1407136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531347631.558, "dur": 4.268, + "args": { + "External id": 1407137,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347633.300, "dur": 2.309, + "args": { + "External id": 1407138,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531347639.668, "dur": 43.369, + "args": { + "External id": 1407139,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531347641.045, "dur": 41.432, + "args": { + "External id": 1407140,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347687.003, "dur": 16.600, + "args": { + "External id": 1407141,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531347709.686, "dur": 5.587, + "args": { + "External id": 1407142,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347713.795, "dur": 0.465, + "args": { + "External id": 1407143,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531347719.274, "dur": 45.818, + "args": { + "External id": 1407144,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531347720.430, "dur": 3.463, + "args": { + "External id": 1407145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531347721.359, "dur": 1.971, + "args": { + "External id": 1407146,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347722.554, "dur": 0.596, + "args": { + "External id": 1407147,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531347724.498, "dur": 40.260, + "args": { + "External id": 1407148,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531347725.033, "dur": 39.148, + "args": { + "External id": 1407149,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531347769.992, "dur": 3.621, + "args": { + "External id": 1407150,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347771.953, "dur": 0.557, + "args": { + "External id": 1407151,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531347781.103, "dur": 1.321, + "args": { + "External id": 1407152,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531347790.366, "dur": 6.364, + "args": { + "External id": 1407153,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531347792.084, "dur": 4.366, + "args": { + "External id": 1407154,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531347882.408, "dur": 224.915, + "args": { + "External id": 1407155,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531347884.241, "dur": 1.886, + "args": { + "External id": 1407156,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531347891.183, "dur": 215.575, + "args": { + "External id": 1407157,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531347892.239, "dur": 0.503, + "args": { + "External id": 1407158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531347893.587, "dur": 20.111, + "args": { + "External id": 1407159,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531347915.437, "dur": 4.296, + "args": { + "External id": 1407160,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531347917.303, "dur": 2.048, + "args": { + "External id": 1407161,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531347920.441, "dur": 20.011, + "args": { + "External id": 1407162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531347921.230, "dur": 1.335, + "args": { + "External id": 1407163,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531347923.692, "dur": 16.506, + "args": { + "External id": 1407164,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347926.152, "dur": 2.242, + "args": { + "External id": 1407165,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531347944.027, "dur": 20.548, + "args": { + "External id": 1407166,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347966.003, "dur": 12.829, + "args": { + "External id": 1407167,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531347981.864, "dur": 12.548, + "args": { + "External id": 1407168,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531347995.673, "dur": 11.396, + "args": { + "External id": 1407169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531348008.412, "dur": 19.887, + "args": { + "External id": 1407170,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348010.328, "dur": 1.890, + "args": { + "External id": 1407171,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348013.905, "dur": 1.487, + "args": { + "External id": 1407172,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348031.417, "dur": 11.785, + "args": { + "External id": 1407173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348044.250, "dur": 60.476, + "args": { + "External id": 1407174,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531348117.248, "dur": 2.397, + "args": { + "External id": 1407175,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531348128.886, "dur": 3.986, + "args": { + "External id": 1407176,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348131.339, "dur": 0.638, + "args": { + "External id": 1407177,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531348211.534, "dur": 63.465, + "args": { + "External id": 1407178,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531348279.768, "dur": 4.766, + "args": { + "External id": 1407179,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348282.639, "dur": 0.713, + "args": { + "External id": 1407180,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348288.382, "dur": 36.694, + "args": { + "External id": 1407181,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531348329.706, "dur": 6.531, + "args": { + "External id": 1407182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531348331.335, "dur": 4.211, + "args": { + "External id": 1407183,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348333.066, "dur": 2.272, + "args": { + "External id": 1407184,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531348338.841, "dur": 44.831, + "args": { + "External id": 1407185,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531348340.047, "dur": 43.034, + "args": { + "External id": 1407186,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348387.674, "dur": 14.374, + "args": { + "External id": 1407187,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531348410.121, "dur": 3.738, + "args": { + "External id": 1407188,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348412.352, "dur": 0.614, + "args": { + "External id": 1407189,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531348433.840, "dur": 53.115, + "args": { + "External id": 1407190,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531348434.839, "dur": 4.614, + "args": { + "External id": 1407191,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531348435.977, "dur": 2.749, + "args": { + "External id": 1407192,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348437.531, "dur": 0.908, + "args": { + "External id": 1407193,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531348442.319, "dur": 44.259, + "args": { + "External id": 1407194,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531348442.890, "dur": 43.128, + "args": { + "External id": 1407195,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531348491.611, "dur": 3.602, + "args": { + "External id": 1407196,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348493.308, "dur": 0.565, + "args": { + "External id": 1407197,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531348500.812, "dur": 1.696, + "args": { + "External id": 1407198,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531348511.493, "dur": 11.011, + "args": { + "External id": 1407199,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531348515.726, "dur": 6.512, + "args": { + "External id": 1407200,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531348610.414, "dur": 194.711, + "args": { + "External id": 1407201,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531348612.657, "dur": 1.837, + "args": { + "External id": 1407202,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531348617.100, "dur": 187.627, + "args": { + "External id": 1407203,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531348618.389, "dur": 0.365, + "args": { + "External id": 1407204,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531348619.917, "dur": 23.149, + "args": { + "External id": 1407205,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531348644.579, "dur": 3.927, + "args": { + "External id": 1407206,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348646.448, "dur": 1.737, + "args": { + "External id": 1407207,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531348651.659, "dur": 22.023, + "args": { + "External id": 1407208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531348652.703, "dur": 1.376, + "args": { + "External id": 1407209,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531348655.233, "dur": 18.199, + "args": { + "External id": 1407210,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348657.741, "dur": 2.391, + "args": { + "External id": 1407211,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531348675.128, "dur": 22.405, + "args": { + "External id": 1407212,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348698.955, "dur": 13.881, + "args": { + "External id": 1407213,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531348715.513, "dur": 19.178, + "args": { + "External id": 1407214,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348735.893, "dur": 13.527, + "args": { + "External id": 1407215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531348751.143, "dur": 24.447, + "args": { + "External id": 1407216,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348753.054, "dur": 1.607, + "args": { + "External id": 1407217,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348758.910, "dur": 1.705, + "args": { + "External id": 1407218,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348777.036, "dur": 13.458, + "args": { + "External id": 1407219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348791.750, "dur": 11.823, + "args": { + "External id": 1407220,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531348811.668, "dur": 1.535, + "args": { + "External id": 1407221,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531348820.829, "dur": 3.373, + "args": { + "External id": 1407222,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348823.035, "dur": 0.297, + "args": { + "External id": 1407223,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531348885.639, "dur": 53.092, + "args": { + "External id": 1407224,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531348943.497, "dur": 6.500, + "args": { + "External id": 1407225,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348948.334, "dur": 0.511, + "args": { + "External id": 1407226,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531348951.551, "dur": 25.142, + "args": { + "External id": 1407227,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531348980.858, "dur": 5.360, + "args": { + "External id": 1407228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531348982.153, "dur": 3.415, + "args": { + "External id": 1407229,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531348984.400, "dur": 0.970, + "args": { + "External id": 1407230,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531348988.694, "dur": 43.591, + "args": { + "External id": 1407231,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531348992.021, "dur": 39.705, + "args": { + "External id": 1407232,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349035.837, "dur": 14.344, + "args": { + "External id": 1407233,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531349102.459, "dur": 6.320, + "args": { + "External id": 1407234,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349106.374, "dur": 0.886, + "args": { + "External id": 1407235,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531349114.576, "dur": 53.756, + "args": { + "External id": 1407236,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531349115.498, "dur": 5.864, + "args": { + "External id": 1407237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531349116.553, "dur": 4.241, + "args": { + "External id": 1407238,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349120.101, "dur": 0.527, + "args": { + "External id": 1407239,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531349122.143, "dur": 45.836, + "args": { + "External id": 1407240,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531349122.672, "dur": 44.569, + "args": { + "External id": 1407241,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531349173.687, "dur": 4.754, + "args": { + "External id": 1407242,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349175.428, "dur": 1.775, + "args": { + "External id": 1407243,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531349184.847, "dur": 1.504, + "args": { + "External id": 1407244,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531349195.234, "dur": 8.274, + "args": { + "External id": 1407245,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531349199.247, "dur": 3.972, + "args": { + "External id": 1407246,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531349291.276, "dur": 209.757, + "args": { + "External id": 1407247,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531349295.060, "dur": 1.792, + "args": { + "External id": 1407248,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531349298.292, "dur": 202.238, + "args": { + "External id": 1407249,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531349299.857, "dur": 0.561, + "args": { + "External id": 1407250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531349301.572, "dur": 21.129, + "args": { + "External id": 1407251,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531349324.394, "dur": 3.921, + "args": { + "External id": 1407252,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349327.507, "dur": 0.567, + "args": { + "External id": 1407253,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531349331.503, "dur": 19.920, + "args": { + "External id": 1407254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531349332.651, "dur": 1.126, + "args": { + "External id": 1407255,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531349334.719, "dur": 16.480, + "args": { + "External id": 1407256,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349337.255, "dur": 2.872, + "args": { + "External id": 1407257,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531349352.857, "dur": 22.254, + "args": { + "External id": 1407258,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349376.754, "dur": 15.025, + "args": { + "External id": 1407259,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531349394.754, "dur": 14.291, + "args": { + "External id": 1407260,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349410.476, "dur": 29.965, + "args": { + "External id": 1407261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531349443.402, "dur": 27.785, + "args": { + "External id": 1407262,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349449.516, "dur": 2.142, + "args": { + "External id": 1407263,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349453.703, "dur": 0.738, + "args": { + "External id": 1407264,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349472.740, "dur": 14.240, + "args": { + "External id": 1407265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349488.140, "dur": 11.166, + "args": { + "External id": 1407266,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531349508.781, "dur": 2.156, + "args": { + "External id": 1407267,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531349520.111, "dur": 3.906, + "args": { + "External id": 1407268,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349522.733, "dur": 0.434, + "args": { + "External id": 1407269,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531349593.455, "dur": 57.225, + "args": { + "External id": 1407270,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531349655.528, "dur": 4.318, + "args": { + "External id": 1407271,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349658.121, "dur": 0.567, + "args": { + "External id": 1407272,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349661.271, "dur": 25.499, + "args": { + "External id": 1407273,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531349691.233, "dur": 7.925, + "args": { + "External id": 1407274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531349692.880, "dur": 5.557, + "args": { + "External id": 1407275,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349696.940, "dur": 1.347, + "args": { + "External id": 1407276,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531349701.769, "dur": 42.096, + "args": { + "External id": 1407277,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531349703.083, "dur": 40.092, + "args": { + "External id": 1407278,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349747.644, "dur": 14.985, + "args": { + "External id": 1407279,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531349768.517, "dur": 3.199, + "args": { + "External id": 1407280,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349770.462, "dur": 0.453, + "args": { + "External id": 1407281,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410531349775.614, "dur": 46.164, + "args": { + "External id": 1407282,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531349778.324, "dur": 3.595, + "args": { + "External id": 1407283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531349779.431, "dur": 1.983, + "args": { + "External id": 1407284,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349780.568, "dur": 0.681, + "args": { + "External id": 1407285,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531349782.708, "dur": 38.784, + "args": { + "External id": 1407286,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531349783.537, "dur": 37.348, + "args": { + "External id": 1407287,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531349825.635, "dur": 3.329, + "args": { + "External id": 1407288,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349827.206, "dur": 0.651, + "args": { + "External id": 1407289,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531349836.113, "dur": 1.388, + "args": { + "External id": 1407290,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531349845.282, "dur": 6.167, + "args": { + "External id": 1407291,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531349847.309, "dur": 3.846, + "args": { + "External id": 1407292,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531349928.789, "dur": 233.346, + "args": { + "External id": 1407293,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531349932.119, "dur": 3.991, + "args": { + "External id": 1407294,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410531349939.283, "dur": 222.194, + "args": { + "External id": 1407295,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410531349940.248, "dur": 0.320, + "args": { + "External id": 1407296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410531349941.817, "dur": 20.646, + "args": { + "External id": 1407297,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410531349963.905, "dur": 4.812, + "args": { + "External id": 1407298,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531349967.684, "dur": 0.789, + "args": { + "External id": 1407299,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531349969.589, "dur": 19.061, + "args": { + "External id": 1407300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410531349970.639, "dur": 1.128, + "args": { + "External id": 1407301,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410531349972.729, "dur": 15.661, + "args": { + "External id": 1407302,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531349975.029, "dur": 1.998, + "args": { + "External id": 1407303,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410531349990.005, "dur": 19.682, + "args": { + "External id": 1407304,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350011.175, "dur": 12.167, + "args": { + "External id": 1407305,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410531350028.214, "dur": 13.538, + "args": { + "External id": 1407306,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350042.984, "dur": 11.799, + "args": { + "External id": 1407307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531350104.075, "dur": 26.015, + "args": { + "External id": 1407308,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350106.530, "dur": 2.559, + "args": { + "External id": 1407309,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531350111.117, "dur": 0.722, + "args": { + "External id": 1407310,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350131.502, "dur": 13.580, + "args": { + "External id": 1407311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350148.531, "dur": 11.508, + "args": { + "External id": 1407312,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410531350170.428, "dur": 2.348, + "args": { + "External id": 1407313,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531350181.350, "dur": 3.763, + "args": { + "External id": 1407314,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531350183.621, "dur": 0.573, + "args": { + "External id": 1407315,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531350253.539, "dur": 61.791, + "args": { + "External id": 1407316,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410531350320.434, "dur": 4.558, + "args": { + "External id": 1407317,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531350323.159, "dur": 0.593, + "args": { + "External id": 1407318,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350326.729, "dur": 26.275, + "args": { + "External id": 1407319,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410531350357.672, "dur": 7.794, + "args": { + "External id": 1407320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410531350361.455, "dur": 3.252, + "args": { + "External id": 1407321,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531350363.375, "dur": 1.128, + "args": { + "External id": 1407322,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410531350368.431, "dur": 42.519, + "args": { + "External id": 1407323,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410531350369.636, "dur": 40.457, + "args": { + "External id": 1407324,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350429.010, "dur": 20.385, + "args": { + "External id": 1407325,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531350455.110, "dur": 31.246, + "args": { + "External id": 1407326,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 16290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410531350457.506, "dur": 28.450, + "args": { + "External id": 1407327,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531350464.183, "dur": 0.806, + "args": { + "External id": 1407328,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 16292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410531350491.879, "dur": 27.974, + "args": { + "External id": 1407329,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 16293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410531350495.977, "dur": 23.669, + "args": { + "External id": 1407330,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 16294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531350500.678, "dur": 3.919, + "args": { + "External id": 1407331,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350505.751, "dur": 13.430, + "args": { + "External id": 1407332,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531350532.383, "dur": 5.000, + "args": { + "External id": 1407333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 16297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531350534.373, "dur": 2.726, + "args": { + "External id": 1407334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 16298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531350538.270, "dur": 2.896, + "args": { + "External id": 1407335,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410531350540.606, "dur": 0.469, + "args": { + "External id": 1407336,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350582.186, "dur": 21.351, + "args": { + "External id": 1407337,"Sequence number": 15109066, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 16301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350605.842, "dur": 12.211, + "args": { + "External id": 1407338,"Sequence number": 15109067, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 16302 + } + }, + { + "ph": "s", "id": 2, "pid": 2338710, "tid": 2338710, "ts": 6410531350605.842, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410531350722.871, "dur": 43.221, + "args": { + "External id": 1407339,"Record function id": 0, "Ev Idx": 16303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338710, "tid": 2338710, + "ts": 6410531350889.974, "dur": 31.655, + "args": { + "External id": 1407340,"Sequence number": 15109068, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 16304 + } + }, + { + "ph": "s", "id": 1, "pid": 2338710, "tid": 2338710, "ts": 6410531350889.974, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531350955.664, "dur": 45.298, + "args": { + "External id": 1407341,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 16305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410531350975.528, "dur": 8.358, + "args": { + "External id": 1407342,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 16306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410531350979.405, "dur": 3.946, + "args": { + "External id": 1407343,"Record function id": 0, "Concrete Inputs": ["[1]", "[1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410531350985.719, "dur": 14.900, + "args": { + "External id": 1407344,"Record function id": 0, "Concrete Inputs": ["", "1."], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 16308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338710, "tid": 2338710, + "ts": 6410533441930.496, "dur": 81.016, + "args": { + "External id": 1407345,"Sequence number": 15109069, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 16309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338710, "tid": 2338710, + "ts": 6410533442023.534, "dur": 21.517, + "args": { + "External id": 1407346,"Sequence number": 15109070, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 16310 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 2338710, "tid": 2338710, + "ts": 6410533442129.865, "dur": 2863.211, + "args": { + "External id": 1407347,"Record function id": 0, "Ev Idx": 16311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533443786.709, "dur": 5.988, + "args": { + "External id": 1407348,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338710, "tid": 2338710, + "ts": 6410533443820.288, "dur": 7.507, + "args": { + "External id": 1407349,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 16313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533444360.323, "dur": 5.800, + "args": { + "External id": 1407350,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338710, "tid": 2338710, + "ts": 6410533444376.991, "dur": 4.044, + "args": { + "External id": 1407351,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 16315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533444846.395, "dur": 3.664, + "args": { + "External id": 1407352,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338710, "tid": 2338710, + "ts": 6410533444861.190, "dur": 3.497, + "args": { + "External id": 1407353,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 16317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533445502.511, "dur": 15.632, + "args": { + "External id": 1407354,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], []], "Ev Idx": 16318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533445511.020, "dur": 2.748, + "args": { + "External id": 1407355,"Record function id": 0, "Concrete Inputs": ["", "[8, 8192]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 16319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533445519.829, "dur": 4.754, + "args": { + "External id": 1407356,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], []], "Ev Idx": 16320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533445522.099, "dur": 1.228, + "args": { + "External id": 1407357,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 16321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533445556.344, "dur": 14350.711, + "args": { + "External id": 1407358,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], [], []], "Ev Idx": 16322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533445563.373, "dur": 14342.814, + "args": { + "External id": 1407359,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], []], "Ev Idx": 16323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533445569.194, "dur": 10.252, + "args": { + "External id": 1407360,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "[4096, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533445581.537, "dur": 14322.580, + "args": { + "External id": 1407361,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 16325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533445591.716, "dur": 0.264, + "args": { + "External id": 1407362,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 16326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533445594.864, "dur": 9.607, + "args": { + "External id": 1407363,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[8192, 1], [4096, 1]], "Input Dims": [[8, 4096], [8, 4096]], "Ev Idx": 16327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338710, "tid": 2338710, + "ts": 6410533445597.700, "dur": 6.618, + "args": { + "External id": 1407364,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], []], "Input Dims": [[8, 4096], [], []], "Ev Idx": 16328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533445603.282, "dur": 0.802, + "args": { + "External id": 1407365,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 16329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410533445606.691, "dur": 122.422, + "args": { + "External id": 1407366,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 16330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410533445609.196, "dur": 119.610, + "args": { + "External id": 1407367,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 16331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533445611.279, "dur": 10.033, + "args": { + "External id": 1407368,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 16332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533445615.951, "dur": 4.860, + "args": { + "External id": 1407369,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533445622.456, "dur": 106.023, + "args": { + "External id": 1407370,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 16334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533445730.842, "dur": 14166.459, + "args": { + "External id": 1407371,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 16335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533459930.226, "dur": 406.838, + "args": { + "External id": 1407372,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], [], []], "Ev Idx": 16336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533459932.980, "dur": 403.446, + "args": { + "External id": 1407373,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], []], "Ev Idx": 16337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533459939.925, "dur": 11.141, + "args": { + "External id": 1407374,"Record function id": 0, "Concrete Inputs": ["[8, 8192]", "[8192, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533459952.504, "dur": 380.981, + "args": { + "External id": 1407375,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[8192, 1], [8192, 1], []], "Input Dims": [[8, 8192], [8, 8192], []], "Ev Idx": 16339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 2338710, "tid": 2338710, + "ts": 6410533460368.345, "dur": 71.411, + "args": { + "External id": 1407376,"Record function id": 0, "Concrete Inputs": ["0", "4096", "", "", "", "False"], "Input type": ["Scalar", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533460374.395, "dur": 7.392, + "args": { + "External id": 1407377,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 2338710, "tid": 2338710, + "ts": 6410533460384.009, "dur": 55.068, + "args": { + "External id": 1407378,"Record function id": 0, "Concrete Inputs": ["0", "4096", "1", ""], "Input type": ["Scalar", "Scalar", "Scalar", "long int"], "Input Strides": [[], [], [], [1]], "Input Dims": [[], [], [], [0]], "Ev Idx": 16342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410533460388.097, "dur": 6.827, + "args": { + "External id": 1407379,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["long int", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::repeat", "pid": 2338710, "tid": 2338710, + "ts": 6410533460454.471, "dur": 73.420, + "args": { + "External id": 1407380,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338710, "tid": 2338710, + "ts": 6410533460459.233, "dur": 5.520, + "args": { + "External id": 1407381,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[4096], [], []], "Ev Idx": 16345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533460462.340, "dur": 2.091, + "args": { + "External id": 1407382,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "[4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533460466.101, "dur": 4.562, + "args": { + "External id": 1407383,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410533460473.192, "dur": 1.909, + "args": { + "External id": 1407384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[4096, 1]], "Input Dims": [[8, 4096]], "Ev Idx": 16348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338710, "tid": 2338710, + "ts": 6410533460480.107, "dur": 7.451, + "args": { + "External id": 1407385,"Record function id": 0, "Concrete Inputs": ["", "0", "1", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 16349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533460486.431, "dur": 0.605, + "args": { + "External id": 1407386,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1]", "[4096, 1, 4096]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 16350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338710, "tid": 2338710, + "ts": 6410533460488.544, "dur": 3.223, + "args": { + "External id": 1407387,"Record function id": 0, "Concrete Inputs": ["", "1", "4096", "4096"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[8, 4096, 1], [], [], []], "Ev Idx": 16351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533460490.737, "dur": 0.954, + "args": { + "External id": 1407388,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "[4096, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[8, 4096, 1], [], [], []], "Ev Idx": 16352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533460494.047, "dur": 4.240, + "args": { + "External id": 1407389,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[4096, 1], [4096, 4096, 4096, 1]], "Input Dims": [[1, 4096], [8, 1, 1, 4096]], "Ev Idx": 16353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338710, "tid": 2338710, + "ts": 6410533460495.863, "dur": 2.300, + "args": { + "External id": 1407390,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1, 4096], [], []], "Ev Idx": 16354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533460497.197, "dur": 0.744, + "args": { + "External id": 1407391,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "[0, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 16355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533460499.407, "dur": 27.694, + "args": { + "External id": 1407392,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 4096, 4096, 1], [0, 4096, 4096, 1], []], "Input Dims": [[8, 1, 1, 4096], [8, 1, 1, 4096], []], "Ev Idx": 16356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533460536.514, "dur": 31.483, + "args": { + "External id": 1407393,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 16357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533460538.653, "dur": 29.120, + "args": { + "External id": 1407394,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], []], "Ev Idx": 16358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533460544.347, "dur": 3.719, + "args": { + "External id": 1407395,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "[4096, 1]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533460548.973, "dur": 18.421, + "args": { + "External id": 1407396,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 16360 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_pre_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533460701.882, "dur": 172.149, + "args": { + "External id": 1407397,"Record function id": 0, "Ev Idx": 16361 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 2338710, "tid": 2338710, + "ts": 6410533460798.315, "dur": 65.210, + "args": { + "External id": 1407398,"Record function id": 0, "Ev Idx": 16362 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533460881.145, "dur": 49.510, + "args": { + "External id": 1407399,"Record function id": 0, "Ev Idx": 16363 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533460939.968, "dur": 14113.052, + "args": { + "External id": 1407400,"Record function id": 0, "Ev Idx": 16364 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 2338710, "tid": 2338710, + "ts": 6410533460948.396, "dur": 1955.137, + "args": { + "External id": 1407401,"Record function id": 0, "Ev Idx": 16365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533461166.091, "dur": 17.264, + "args": { + "External id": 1407402,"Record function id": 0, "Concrete Inputs": ["[141824512]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533461203.788, "dur": 152.894, + "args": { + "External id": 1407403,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[141824512], [], []], "Ev Idx": 16367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461210.421, "dur": 1.678, + "args": { + "External id": 1407404,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461217.141, "dur": 0.274, + "args": { + "External id": 1407405,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461219.367, "dur": 0.529, + "args": { + "External id": 1407406,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "16384512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461222.060, "dur": 0.315, + "args": { + "External id": 1407407,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "18481664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461226.438, "dur": 0.386, + "args": { + "External id": 1407408,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19005952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461229.075, "dur": 0.436, + "args": { + "External id": 1407409,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "19530240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461231.245, "dur": 2.104, + "args": { + "External id": 1407410,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461235.062, "dur": 2.795, + "args": { + "External id": 1407411,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "21627904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461239.564, "dur": 0.405, + "args": { + "External id": 1407412,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "28967936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461243.989, "dur": 0.438, + "args": { + "External id": 1407413,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "36307968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461246.066, "dur": 0.536, + "args": { + "External id": 1407414,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461248.214, "dur": 0.343, + "args": { + "External id": 1407415,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "43648512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461251.682, "dur": 0.558, + "args": { + "External id": 1407416,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "45745664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461253.911, "dur": 0.470, + "args": { + "External id": 1407417,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "46269952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461256.333, "dur": 2.414, + "args": { + "External id": 1407418,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "46794240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461260.833, "dur": 2.420, + "args": { + "External id": 1407419,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461264.802, "dur": 0.620, + "args": { + "External id": 1407420,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "48891904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461269.774, "dur": 0.542, + "args": { + "External id": 1407421,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "56231936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461272.213, "dur": 0.554, + "args": { + "External id": 1407422,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "63571968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461274.573, "dur": 0.322, + "args": { + "External id": 1407423,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461278.353, "dur": 0.582, + "args": { + "External id": 1407424,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "70912512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461280.415, "dur": 0.460, + "args": { + "External id": 1407425,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73009664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461282.743, "dur": 2.885, + "args": { + "External id": 1407426,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73533952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461287.388, "dur": 3.214, + "args": { + "External id": 1407427,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "74058240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461292.311, "dur": 0.497, + "args": { + "External id": 1407428,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461295.971, "dur": 0.661, + "args": { + "External id": 1407429,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "76155904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461298.395, "dur": 0.507, + "args": { + "External id": 1407430,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "83495936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461300.632, "dur": 0.345, + "args": { + "External id": 1407431,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "90835968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461304.382, "dur": 0.456, + "args": { + "External id": 1407432,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461306.522, "dur": 0.540, + "args": { + "External id": 1407433,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "98176512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461308.480, "dur": 2.582, + "args": { + "External id": 1407434,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100273664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461312.553, "dur": 2.507, + "args": { + "External id": 1407435,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100797952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461316.636, "dur": 0.705, + "args": { + "External id": 1407436,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "101322240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461321.660, "dur": 0.455, + "args": { + "External id": 1407437,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461323.742, "dur": 0.578, + "args": { + "External id": 1407438,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "103419904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461326.462, "dur": 0.349, + "args": { + "External id": 1407439,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "110759936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461330.901, "dur": 0.527, + "args": { + "External id": 1407440,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "118099968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461333.335, "dur": 0.647, + "args": { + "External id": 1407441,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461335.615, "dur": 2.309, + "args": { + "External id": 1407442,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "125440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533461391.942, "dur": 166.080, + "args": { + "External id": 1407443,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 16407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533461658.685, "dur": 386.980, + "args": { + "External id": 1407444,"Record function id": 0, "Concrete Inputs": ["", "", "141824512", "8", "4", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 16408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533461678.397, "dur": 10.045, + "args": { + "External id": 1407445,"Record function id": 0, "Concrete Inputs": ["[1134596096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533461695.643, "dur": 16.116, + "args": { + "External id": 1407446,"Record function id": 0, "Concrete Inputs": ["", "0", "567298048", "141824512"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1134596096], [], [], []], "Ev Idx": 16410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533461703.096, "dur": 8.192, + "args": { + "External id": 1407447,"Record function id": 0, "Concrete Inputs": ["", "0", "567298048", "709122560", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[1134596096], [], [], [], []], "Ev Idx": 16411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461706.758, "dur": 0.998, + "args": { + "External id": 1407448,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "[1]", "567298048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1134596096], [], [], []], "Ev Idx": 16412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533461720.839, "dur": 134.383, + "args": { + "External id": 1407449,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[141824512], [], []], "Ev Idx": 16413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461723.512, "dur": 0.526, + "args": { + "External id": 1407450,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "567298048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461725.449, "dur": 3.152, + "args": { + "External id": 1407451,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "583682048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461730.797, "dur": 0.540, + "args": { + "External id": 1407452,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "583682560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461733.490, "dur": 0.474, + "args": { + "External id": 1407453,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "585779712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461737.567, "dur": 0.612, + "args": { + "External id": 1407454,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "586304000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461739.930, "dur": 0.349, + "args": { + "External id": 1407455,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "586828288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461741.824, "dur": 2.882, + "args": { + "External id": 1407456,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "588925440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461748.260, "dur": 0.568, + "args": { + "External id": 1407457,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "588925952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461750.563, "dur": 0.501, + "args": { + "External id": 1407458,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "596265984"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461752.757, "dur": 2.488, + "args": { + "External id": 1407459,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "603606016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461756.648, "dur": 0.633, + "args": { + "External id": 1407460,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "610946048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461759.328, "dur": 0.639, + "args": { + "External id": 1407461,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "610946560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461764.413, "dur": 0.485, + "args": { + "External id": 1407462,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "613043712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461766.543, "dur": 0.399, + "args": { + "External id": 1407463,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "613568000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461768.425, "dur": 2.667, + "args": { + "External id": 1407464,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "614092288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461775.430, "dur": 0.579, + "args": { + "External id": 1407465,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "616189440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461777.682, "dur": 0.545, + "args": { + "External id": 1407466,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "616189952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461779.447, "dur": 2.213, + "args": { + "External id": 1407467,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "623529984"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461783.671, "dur": 0.607, + "args": { + "External id": 1407468,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "630870016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461785.902, "dur": 0.467, + "args": { + "External id": 1407469,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "638210048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461789.376, "dur": 0.527, + "args": { + "External id": 1407470,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "638210560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461791.223, "dur": 0.384, + "args": { + "External id": 1407471,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "640307712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461793.390, "dur": 2.672, + "args": { + "External id": 1407472,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "640832000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461799.657, "dur": 0.592, + "args": { + "External id": 1407473,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "641356288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461801.405, "dur": 0.461, + "args": { + "External id": 1407474,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "643453440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461803.396, "dur": 1.871, + "args": { + "External id": 1407475,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "643453952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461806.413, "dur": 0.821, + "args": { + "External id": 1407476,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "650793984"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461808.415, "dur": 0.517, + "args": { + "External id": 1407477,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "658134016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461812.139, "dur": 0.659, + "args": { + "External id": 1407478,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "665474048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461813.876, "dur": 0.307, + "args": { + "External id": 1407479,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "665474560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461815.658, "dur": 2.846, + "args": { + "External id": 1407480,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "667571712"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461821.587, "dur": 0.331, + "args": { + "External id": 1407481,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "668096000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461823.037, "dur": 0.466, + "args": { + "External id": 1407482,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "668620288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461824.463, "dur": 3.053, + "args": { + "External id": 1407483,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "670717440"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461828.484, "dur": 0.673, + "args": { + "External id": 1407484,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "670717952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461830.427, "dur": 0.590, + "args": { + "External id": 1407485,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "678057984"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461833.953, "dur": 0.556, + "args": { + "External id": 1407486,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "685398016"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461835.362, "dur": 0.276, + "args": { + "External id": 1407487,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "692738048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533461836.981, "dur": 2.123, + "args": { + "External id": 1407488,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "692738560"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533461909.461, "dur": 119.121, + "args": { + "External id": 1413633,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 16453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533462153.706, "dur": 564.725, + "args": { + "External id": 1413634,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[1134596096], [141824512], [], [], []], "Ev Idx": 16454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533462191.856, "dur": 518.094, + "args": { + "External id": 1413635,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1134596096, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[141824512], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16455, "In msg nelems": 141824512 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533462207.698, "dur": 492.913, + "args": { + "External id": 1413636,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[141824512]], "Ev Idx": 16456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533462761.907, "dur": 3.742, + "args": { + "External id": 1413637,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 16457, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 2338710, "tid": 2338710, + "ts": 6410533462925.987, "dur": 11811.614, + "args": { + "External id": 1413638,"Record function id": 0, "Ev Idx": 16458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463350.306, "dur": 9.320, + "args": { + "External id": 1413639,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1134596096], []], "Ev Idx": 16459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463365.970, "dur": 1.426, + "args": { + "External id": 1413640,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[131072000], []], "Ev Idx": 16460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463370.292, "dur": 1.605, + "args": { + "External id": 1413641,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463375.757, "dur": 1.643, + "args": { + "External id": 1413642,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463380.055, "dur": 1.363, + "args": { + "External id": 1413643,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463383.943, "dur": 1.696, + "args": { + "External id": 1413644,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463391.004, "dur": 1.532, + "args": { + "External id": 1413645,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463395.240, "dur": 4.999, + "args": { + "External id": 1413646,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463402.840, "dur": 1.184, + "args": { + "External id": 1413647,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463406.485, "dur": 1.264, + "args": { + "External id": 1413648,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463412.966, "dur": 36.675, + "args": { + "External id": 1413649,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463454.938, "dur": 1.701, + "args": { + "External id": 1413650,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463459.180, "dur": 1.167, + "args": { + "External id": 1413651,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463462.706, "dur": 1.366, + "args": { + "External id": 1413652,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463469.134, "dur": 0.978, + "args": { + "External id": 1413653,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463472.919, "dur": 5.586, + "args": { + "External id": 1413654,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463481.066, "dur": 1.081, + "args": { + "External id": 1413655,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463484.774, "dur": 1.204, + "args": { + "External id": 1413656,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463495.447, "dur": 1.342, + "args": { + "External id": 1413657,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463499.139, "dur": 1.217, + "args": { + "External id": 1413658,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463502.698, "dur": 1.405, + "args": { + "External id": 1413659,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463506.991, "dur": 1.342, + "args": { + "External id": 1413660,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463513.375, "dur": 0.964, + "args": { + "External id": 1413661,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463516.761, "dur": 5.368, + "args": { + "External id": 1413662,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463524.749, "dur": 1.200, + "args": { + "External id": 1413663,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463528.670, "dur": 1.349, + "args": { + "External id": 1413664,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463535.818, "dur": 1.069, + "args": { + "External id": 1413665,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463539.133, "dur": 1.340, + "args": { + "External id": 1413666,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463543.762, "dur": 1.283, + "args": { + "External id": 1413667,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463547.334, "dur": 1.145, + "args": { + "External id": 1413668,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463553.818, "dur": 1.820, + "args": { + "External id": 1413669,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463558.032, "dur": 5.387, + "args": { + "External id": 1413670,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463566.085, "dur": 1.015, + "args": { + "External id": 1413671,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463569.353, "dur": 1.103, + "args": { + "External id": 1413672,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463575.780, "dur": 1.328, + "args": { + "External id": 1413673,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463579.289, "dur": 0.986, + "args": { + "External id": 1413674,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463582.629, "dur": 1.003, + "args": { + "External id": 1413675,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463585.742, "dur": 1.394, + "args": { + "External id": 1413676,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463594.375, "dur": 1.155, + "args": { + "External id": 1413677,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533463597.803, "dur": 4.570, + "args": { + "External id": 1413678,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[131072000], []], "Ev Idx": 16498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533463646.596, "dur": 10990.307, + "args": { + "External id": 1413679,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[141824512, 1], [], [], []], "Input Dims": [[8, 141824512], [], [], []], "Ev Idx": 16499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533463684.021, "dur": 10932.038, + "args": { + "External id": 1413680,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[141824512, 1], [], [], []], "Input Dims": [[8, 141824512], [], [], []], "Ev Idx": 16500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533463717.515, "dur": 21.581, + "args": { + "External id": 1413681,"Record function id": 0, "Concrete Inputs": ["[4384]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533463748.082, "dur": 10775.142, + "args": { + "External id": 1413682,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[4384], [], [], [], [], [], [], []], "Ev Idx": 16502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533463751.478, "dur": 10770.183, + "args": { + "External id": 1413683,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[4384], [], [], [], [], [], []], "Ev Idx": 16503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533463759.273, "dur": 10.451, + "args": { + "External id": 1413684,"Record function id": 0, "Concrete Inputs": ["[4384]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533463774.758, "dur": 10739.763, + "args": { + "External id": 1413685,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4384], [4384], []], "Ev Idx": 16505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533475239.006, "dur": 49.134, + "args": { + "External id": 1413686,"Record function id": 0, "Ev Idx": 16506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 2338710, "tid": 2338710, + "ts": 6410533475290.721, "dur": 377.894, + "args": { + "External id": 1413687,"Record function id": 0, "Ev Idx": 16507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533475359.458, "dur": 294.838, + "args": { + "External id": 1413688,"Sequence number": 15109071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "long int"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32000, 4096], [8, 4096]], "Ev Idx": 16508 + } + }, + { + "ph": "s", "id": 448, "pid": 2338710, "tid": 2338710, "ts": 6410533475359.458, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533475517.096, "dur": 78.172, + "args": { + "External id": 1413689,"kernel_hash": "cvykvfdpfag3zvgkkgm7dmy4omdmsmvjcopgv6veoygd3dudukzf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/vy/cvykvfdpfag3zvgkkgm7dmy4omdmsmvjcopgv6veoygd3dudukzf.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096], [32000, 4096], [8, 4096, 4096], []], "Ev Idx": 16509 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533475763.032, "dur": 79.330, + "args": { + "External id": 1413690,"Record function id": 0, "Ev Idx": 16510 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 2338710, "tid": 2338710, + "ts": 6410533475859.037, "dur": 8024.362, + "args": { + "External id": 1413691,"Record function id": 0, "Ev Idx": 16511 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338710, "tid": 2338710, + "ts": 6410533475871.490, "dur": 932.064, + "args": { + "External id": 1413692,"Record function id": 0, "Ev Idx": 16512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533475965.808, "dur": 12.377, + "args": { + "External id": 1413693,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533475993.441, "dur": 41.509, + "args": { + "External id": 1413694,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476002.087, "dur": 2.472, + "args": { + "External id": 1413695,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476007.214, "dur": 0.811, + "args": { + "External id": 1413696,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476009.040, "dur": 2.444, + "args": { + "External id": 1413697,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476012.569, "dur": 2.883, + "args": { + "External id": 1413698,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476016.644, "dur": 0.455, + "args": { + "External id": 1413699,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476020.688, "dur": 0.395, + "args": { + "External id": 1413700,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476022.299, "dur": 0.386, + "args": { + "External id": 1413701,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476023.712, "dur": 0.585, + "args": { + "External id": 1413702,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476027.109, "dur": 0.648, + "args": { + "External id": 1413703,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533476046.199, "dur": 100.378, + "args": { + "External id": 1413704,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533476186.888, "dur": 135.445, + "args": { + "External id": 1413705,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533476200.300, "dur": 6.511, + "args": { + "External id": 1413706,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533476212.781, "dur": 11.652, + "args": { + "External id": 1413707,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533476217.531, "dur": 6.515, + "args": { + "External id": 1413708,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476221.281, "dur": 1.026, + "args": { + "External id": 1413709,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533476231.711, "dur": 33.510, + "args": { + "External id": 1413710,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476234.055, "dur": 2.906, + "args": { + "External id": 1413711,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476238.199, "dur": 0.807, + "args": { + "External id": 1413712,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476242.944, "dur": 0.375, + "args": { + "External id": 1413713,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476244.416, "dur": 0.494, + "args": { + "External id": 1413714,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476245.688, "dur": 2.239, + "args": { + "External id": 1413715,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476249.172, "dur": 0.509, + "args": { + "External id": 1413716,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476250.724, "dur": 0.548, + "args": { + "External id": 1413717,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476254.994, "dur": 0.430, + "args": { + "External id": 1413718,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533476256.464, "dur": 2.714, + "args": { + "External id": 1413719,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533476278.528, "dur": 33.878, + "args": { + "External id": 1413720,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533476381.992, "dur": 321.003, + "args": { + "External id": 1413721,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533476436.984, "dur": 260.625, + "args": { + "External id": 1413722,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16542, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533476449.440, "dur": 242.829, + "args": { + "External id": 1413723,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533476727.684, "dur": 2.245, + "args": { + "External id": 1413724,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 16544, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338710, "tid": 2338710, + "ts": 6410533476824.944, "dur": 6802.871, + "args": { + "External id": 1413725,"Record function id": 0, "Ev Idx": 16545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476949.008, "dur": 6.740, + "args": { + "External id": 1413726,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476959.427, "dur": 1.196, + "args": { + "External id": 1413727,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476962.484, "dur": 1.196, + "args": { + "External id": 1413728,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476965.235, "dur": 1.022, + "args": { + "External id": 1413729,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476967.653, "dur": 1.255, + "args": { + "External id": 1413730,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476972.510, "dur": 1.038, + "args": { + "External id": 1413731,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476975.391, "dur": 1.050, + "args": { + "External id": 1413732,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476978.036, "dur": 4.530, + "args": { + "External id": 1413733,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476984.058, "dur": 0.990, + "args": { + "External id": 1413734,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533476989.160, "dur": 1.268, + "args": { + "External id": 1413735,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533477017.684, "dur": 6547.307, + "args": { + "External id": 1413736,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533477033.859, "dur": 6518.062, + "args": { + "External id": 1413737,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533477050.030, "dur": 54.900, + "args": { + "External id": 1413738,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533477111.853, "dur": 6392.395, + "args": { + "External id": 1413739,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533477114.427, "dur": 6388.658, + "args": { + "External id": 1413740,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533477120.860, "dur": 6.567, + "args": { + "External id": 1413741,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533477129.436, "dur": 6369.289, + "args": { + "External id": 1413742,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533483817.894, "dur": 37.598, + "args": { + "External id": 1413743,"Sequence number": 15109072, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16563 + } + }, + { + "ph": "s", "id": 447, "pid": 2338710, "tid": 2338710, "ts": 6410533483817.894, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533483839.341, "dur": 11.271, + "args": { + "External id": 1413744,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533483844.039, "dur": 6.284, + "args": { + "External id": 1413745,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533483929.610, "dur": 169.952, + "args": { + "External id": 1413746,"Record function id": 0, "Ev Idx": 16566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533484102.401, "dur": 1265.208, + "args": { + "External id": 1413747,"Record function id": 0, "Ev Idx": 16567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533484150.481, "dur": 1202.025, + "args": { + "External id": 1413748,"Sequence number": 15109073, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16568 + } + }, + { + "ph": "s", "id": 446, "pid": 2338710, "tid": 2338710, "ts": 6410533484150.481, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533484235.958, "dur": 59.224, + "args": { + "External id": 1413749,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533484309.792, "dur": 134.419, + "args": { + "External id": 1413750,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533484457.125, "dur": 43.912, + "args": { + "External id": 1413751,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533484512.586, "dur": 30.906, + "args": { + "External id": 1413752,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533484575.803, "dur": 32.972, + "args": { + "External id": 1413753,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533484631.565, "dur": 20.326, + "args": { + "External id": 1413754,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533484677.619, "dur": 156.073, + "args": { + "External id": 1413755,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533484745.154, "dur": 14.172, + "args": { + "External id": 1413756,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533484751.060, "dur": 7.436, + "args": { + "External id": 1413757,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533484762.108, "dur": 4.269, + "args": { + "External id": 1413758,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533484767.892, "dur": 1.153, + "args": { + "External id": 1413759,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533484771.518, "dur": 4.516, + "args": { + "External id": 1413760,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533484844.606, "dur": 49.282, + "args": { + "External id": 1413761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533484929.391, "dur": 33.325, + "args": { + "External id": 1413762,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533484973.812, "dur": 45.545, + "args": { + "External id": 1413763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533485029.550, "dur": 69.823, + "args": { + "External id": 1413764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533485131.555, "dur": 31.411, + "args": { + "External id": 1413765,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533485173.537, "dur": 46.786, + "args": { + "External id": 1413766,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533485240.095, "dur": 21.547, + "args": { + "External id": 1413767,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16587 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.0)", "pid": 2338710, "tid": 2338710, + "ts": 6410533485457.064, "dur": 94.991, + "args": { + "External id": 1413768,"Record function id": 0, "Ev Idx": 16588 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533485634.150, "dur": 50.494, + "args": { + "External id": 1413769,"Record function id": 0, "Ev Idx": 16589 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 2338710, "tid": 2338710, + "ts": 6410533485694.939, "dur": 29251.214, + "args": { + "External id": 1413770,"Record function id": 0, "Ev Idx": 16590 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338710, "tid": 2338710, + "ts": 6410533485702.202, "dur": 992.206, + "args": { + "External id": 1413771,"Record function id": 0, "Ev Idx": 16591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533485793.686, "dur": 9.337, + "args": { + "External id": 1413772,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533485817.650, "dur": 42.615, + "args": { + "External id": 1413773,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485823.488, "dur": 4.588, + "args": { + "External id": 1413774,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485830.082, "dur": 0.684, + "args": { + "External id": 1413775,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485831.700, "dur": 0.686, + "args": { + "External id": 1413776,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485836.560, "dur": 0.463, + "args": { + "External id": 1413777,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485838.190, "dur": 0.600, + "args": { + "External id": 1413778,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485839.966, "dur": 0.537, + "args": { + "External id": 1413779,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485844.051, "dur": 2.462, + "args": { + "External id": 1413780,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485847.794, "dur": 0.549, + "args": { + "External id": 1413781,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533485849.746, "dur": 2.842, + "args": { + "External id": 1413782,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533485879.097, "dur": 57.876, + "args": { + "External id": 1413783,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533485971.849, "dur": 172.300, + "args": { + "External id": 1413784,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533485983.812, "dur": 5.922, + "args": { + "External id": 1413785,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533485995.571, "dur": 10.831, + "args": { + "External id": 1413786,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533486000.236, "dur": 5.770, + "args": { + "External id": 1413787,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486003.780, "dur": 0.483, + "args": { + "External id": 1413788,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533486013.330, "dur": 31.723, + "args": { + "External id": 1413789,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486015.582, "dur": 0.620, + "args": { + "External id": 1413790,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486017.310, "dur": 2.698, + "args": { + "External id": 1413791,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486021.014, "dur": 0.543, + "args": { + "External id": 1413792,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486022.595, "dur": 3.221, + "args": { + "External id": 1413793,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486029.433, "dur": 0.261, + "args": { + "External id": 1413794,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486030.987, "dur": 0.600, + "args": { + "External id": 1413795,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486032.997, "dur": 0.478, + "args": { + "External id": 1413796,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486036.893, "dur": 0.438, + "args": { + "External id": 1413797,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486039.193, "dur": 0.570, + "args": { + "External id": 1413798,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533486096.726, "dur": 37.752, + "args": { + "External id": 1413799,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533486203.416, "dur": 389.481, + "args": { + "External id": 1413800,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533486237.957, "dur": 349.313, + "args": { + "External id": 1413801,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16621, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533486248.166, "dur": 331.658, + "args": { + "External id": 1413802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533486619.062, "dur": 2.709, + "args": { + "External id": 1413803,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 16623, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338710, "tid": 2338710, + "ts": 6410533486715.691, "dur": 27993.231, + "args": { + "External id": 1413804,"Record function id": 0, "Ev Idx": 16624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486831.569, "dur": 6.796, + "args": { + "External id": 1413805,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486842.087, "dur": 1.284, + "args": { + "External id": 1413806,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486844.926, "dur": 3.850, + "args": { + "External id": 1413807,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486850.512, "dur": 0.850, + "args": { + "External id": 1413808,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486852.852, "dur": 0.913, + "args": { + "External id": 1413809,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486857.988, "dur": 1.206, + "args": { + "External id": 1413810,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486860.995, "dur": 1.138, + "args": { + "External id": 1413811,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486863.677, "dur": 3.436, + "args": { + "External id": 1413812,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486868.891, "dur": 0.974, + "args": { + "External id": 1413813,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533486873.861, "dur": 1.163, + "args": { + "External id": 1413814,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533486892.028, "dur": 27752.957, + "args": { + "External id": 1413815,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533486907.929, "dur": 27724.743, + "args": { + "External id": 1413816,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533486928.009, "dur": 16.241, + "args": { + "External id": 1413817,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533486948.242, "dur": 27639.989, + "args": { + "External id": 1413818,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533486951.034, "dur": 27636.075, + "args": { + "External id": 1413819,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533486956.518, "dur": 5.422, + "args": { + "External id": 1413820,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533486963.614, "dur": 27618.533, + "args": { + "External id": 1413821,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533514879.022, "dur": 40.520, + "args": { + "External id": 1413822,"Sequence number": 15109074, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16642 + } + }, + { + "ph": "s", "id": 445, "pid": 2338710, "tid": 2338710, "ts": 6410533514879.022, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533514899.813, "dur": 15.067, + "args": { + "External id": 1413823,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533514908.221, "dur": 6.409, + "args": { + "External id": 1413824,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533514989.136, "dur": 123.293, + "args": { + "External id": 1413825,"Record function id": 0, "Ev Idx": 16645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533515115.617, "dur": 1178.130, + "args": { + "External id": 1413826,"Record function id": 0, "Ev Idx": 16646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533515161.289, "dur": 1117.767, + "args": { + "External id": 1413827,"Sequence number": 15109075, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16647 + } + }, + { + "ph": "s", "id": 444, "pid": 2338710, "tid": 2338710, "ts": 6410533515161.289, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533515235.063, "dur": 52.452, + "args": { + "External id": 1413828,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533515301.983, "dur": 103.542, + "args": { + "External id": 1413829,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533515437.973, "dur": 43.978, + "args": { + "External id": 1413830,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533515491.333, "dur": 30.656, + "args": { + "External id": 1413831,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533515552.655, "dur": 28.069, + "args": { + "External id": 1413832,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533515599.885, "dur": 20.076, + "args": { + "External id": 1413833,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533515645.955, "dur": 144.285, + "args": { + "External id": 1413834,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533515700.070, "dur": 12.947, + "args": { + "External id": 1413835,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533515705.821, "dur": 6.282, + "args": { + "External id": 1413836,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533515715.829, "dur": 7.267, + "args": { + "External id": 1413837,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533515724.466, "dur": 1.357, + "args": { + "External id": 1413838,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533515730.660, "dur": 6.545, + "args": { + "External id": 1413839,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533515800.568, "dur": 48.550, + "args": { + "External id": 1413840,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533515883.055, "dur": 29.792, + "args": { + "External id": 1413841,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533515923.411, "dur": 43.955, + "args": { + "External id": 1413842,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533515973.688, "dur": 35.562, + "args": { + "External id": 1413843,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533516033.049, "dur": 78.822, + "args": { + "External id": 1413844,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533516120.073, "dur": 43.198, + "args": { + "External id": 1413845,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533516183.927, "dur": 19.022, + "args": { + "External id": 1413846,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16666 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.1)", "pid": 2338710, "tid": 2338710, + "ts": 6410533516360.960, "dur": 102.270, + "args": { + "External id": 1413847,"Record function id": 0, "Ev Idx": 16667 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533516542.224, "dur": 49.149, + "args": { + "External id": 1413848,"Record function id": 0, "Ev Idx": 16668 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 2338710, "tid": 2338710, + "ts": 6410533516600.979, "dur": 28872.196, + "args": { + "External id": 1413849,"Record function id": 0, "Ev Idx": 16669 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338710, "tid": 2338710, + "ts": 6410533516609.982, "dur": 968.218, + "args": { + "External id": 1413850,"Record function id": 0, "Ev Idx": 16670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533516706.138, "dur": 9.545, + "args": { + "External id": 1413851,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533516728.684, "dur": 38.619, + "args": { + "External id": 1413852,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516733.911, "dur": 2.392, + "args": { + "External id": 1413853,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516741.192, "dur": 0.422, + "args": { + "External id": 1413854,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516742.850, "dur": 0.532, + "args": { + "External id": 1413855,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516744.668, "dur": 0.929, + "args": { + "External id": 1413856,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516748.933, "dur": 0.437, + "args": { + "External id": 1413857,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516750.541, "dur": 0.420, + "args": { + "External id": 1413858,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516752.201, "dur": 4.396, + "args": { + "External id": 1413859,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516757.797, "dur": 0.380, + "args": { + "External id": 1413860,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516759.151, "dur": 0.346, + "args": { + "External id": 1413861,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533516779.158, "dur": 55.163, + "args": { + "External id": 1413862,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533516868.793, "dur": 130.029, + "args": { + "External id": 1413863,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533516880.178, "dur": 5.253, + "args": { + "External id": 1413864,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533516890.857, "dur": 10.661, + "args": { + "External id": 1413865,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533516895.361, "dur": 5.738, + "args": { + "External id": 1413866,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516899.324, "dur": 0.434, + "args": { + "External id": 1413867,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533516908.103, "dur": 31.422, + "args": { + "External id": 1413868,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516910.054, "dur": 2.782, + "args": { + "External id": 1413869,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516914.282, "dur": 0.269, + "args": { + "External id": 1413870,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516915.965, "dur": 0.600, + "args": { + "External id": 1413871,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516920.118, "dur": 2.893, + "args": { + "External id": 1413872,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516923.804, "dur": 0.285, + "args": { + "External id": 1413873,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516925.214, "dur": 0.269, + "args": { + "External id": 1413874,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516927.694, "dur": 0.323, + "args": { + "External id": 1413875,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516929.172, "dur": 0.284, + "args": { + "External id": 1413876,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533516930.711, "dur": 2.147, + "args": { + "External id": 1413877,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533516955.201, "dur": 34.812, + "args": { + "External id": 1413878,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533517051.455, "dur": 420.597, + "args": { + "External id": 1413879,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533517123.079, "dur": 343.079, + "args": { + "External id": 1413880,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16700, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533517136.384, "dur": 323.414, + "args": { + "External id": 1413881,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533517498.679, "dur": 2.655, + "args": { + "External id": 1413882,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 16702, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338710, "tid": 2338710, + "ts": 6410533517599.610, "dur": 27628.430, + "args": { + "External id": 1413883,"Record function id": 0, "Ev Idx": 16703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517717.143, "dur": 6.769, + "args": { + "External id": 1413884,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517727.490, "dur": 1.137, + "args": { + "External id": 1413885,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517730.367, "dur": 3.725, + "args": { + "External id": 1413886,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517735.757, "dur": 1.654, + "args": { + "External id": 1413887,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517738.930, "dur": 1.044, + "args": { + "External id": 1413888,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517741.530, "dur": 1.095, + "args": { + "External id": 1413889,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517746.458, "dur": 1.229, + "args": { + "External id": 1413890,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517749.749, "dur": 3.074, + "args": { + "External id": 1413891,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517754.406, "dur": 1.266, + "args": { + "External id": 1413892,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533517757.741, "dur": 1.100, + "args": { + "External id": 1413893,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533517779.591, "dur": 27383.404, + "args": { + "External id": 1413894,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533517795.096, "dur": 27354.934, + "args": { + "External id": 1413895,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533517813.519, "dur": 17.470, + "args": { + "External id": 1413896,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533517834.747, "dur": 27271.940, + "args": { + "External id": 1413897,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533517837.392, "dur": 27268.094, + "args": { + "External id": 1413898,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533517843.489, "dur": 5.323, + "args": { + "External id": 1413899,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533517850.442, "dur": 27249.815, + "args": { + "External id": 1413900,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533545396.126, "dur": 48.494, + "args": { + "External id": 1413901,"Sequence number": 15109076, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16721 + } + }, + { + "ph": "s", "id": 443, "pid": 2338710, "tid": 2338710, "ts": 6410533545396.126, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533545426.259, "dur": 13.018, + "args": { + "External id": 1413902,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533545431.779, "dur": 7.100, + "args": { + "External id": 1413903,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533545517.188, "dur": 75.998, + "args": { + "External id": 1413904,"Record function id": 0, "Ev Idx": 16724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533545594.685, "dur": 1168.774, + "args": { + "External id": 1413905,"Record function id": 0, "Ev Idx": 16725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533545636.776, "dur": 1112.510, + "args": { + "External id": 1413906,"Sequence number": 15109077, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16726 + } + }, + { + "ph": "s", "id": 442, "pid": 2338710, "tid": 2338710, "ts": 6410533545636.776, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533545709.100, "dur": 51.683, + "args": { + "External id": 1413907,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533545775.381, "dur": 109.351, + "args": { + "External id": 1413908,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533545897.226, "dur": 39.955, + "args": { + "External id": 1413909,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533545946.679, "dur": 30.641, + "args": { + "External id": 1413910,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533546003.555, "dur": 27.483, + "args": { + "External id": 1413911,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533546051.808, "dur": 57.401, + "args": { + "External id": 1413912,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533546136.488, "dur": 140.538, + "args": { + "External id": 1413913,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533546190.948, "dur": 12.865, + "args": { + "External id": 1413914,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533546196.636, "dur": 6.431, + "args": { + "External id": 1413915,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533546206.676, "dur": 4.392, + "args": { + "External id": 1413916,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533546212.683, "dur": 1.547, + "args": { + "External id": 1413917,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533546216.634, "dur": 7.933, + "args": { + "External id": 1413918,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533546287.830, "dur": 57.705, + "args": { + "External id": 1413919,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533546382.939, "dur": 30.669, + "args": { + "External id": 1413920,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533546441.401, "dur": 46.901, + "args": { + "External id": 1413921,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533546498.426, "dur": 35.632, + "args": { + "External id": 1413922,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533546560.127, "dur": 29.898, + "args": { + "External id": 1413923,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533546598.470, "dur": 36.961, + "args": { + "External id": 1413924,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533546654.805, "dur": 18.195, + "args": { + "External id": 1413925,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16745 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.2)", "pid": 2338710, "tid": 2338710, + "ts": 6410533546829.822, "dur": 83.034, + "args": { + "External id": 1413926,"Record function id": 0, "Ev Idx": 16746 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533546990.819, "dur": 49.576, + "args": { + "External id": 1413927,"Record function id": 0, "Ev Idx": 16747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 2338710, "tid": 2338710, + "ts": 6410533547049.949, "dur": 29657.631, + "args": { + "External id": 1413928,"Record function id": 0, "Ev Idx": 16748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338710, "tid": 2338710, + "ts": 6410533547100.086, "dur": 927.454, + "args": { + "External id": 1413929,"Record function id": 0, "Ev Idx": 16749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533547193.223, "dur": 10.447, + "args": { + "External id": 1413930,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533547217.439, "dur": 41.939, + "args": { + "External id": 1413931,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547223.707, "dur": 2.410, + "args": { + "External id": 1413932,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547230.745, "dur": 0.478, + "args": { + "External id": 1413933,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547232.549, "dur": 0.750, + "args": { + "External id": 1413934,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547234.507, "dur": 0.515, + "args": { + "External id": 1413935,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547238.837, "dur": 0.373, + "args": { + "External id": 1413936,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547240.590, "dur": 0.440, + "args": { + "External id": 1413937,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547242.402, "dur": 4.444, + "args": { + "External id": 1413938,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547248.203, "dur": 0.252, + "args": { + "External id": 1413939,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547249.943, "dur": 0.327, + "args": { + "External id": 1413940,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533547271.737, "dur": 57.621, + "args": { + "External id": 1413941,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533547363.741, "dur": 151.228, + "args": { + "External id": 1413942,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533547375.015, "dur": 4.524, + "args": { + "External id": 1413943,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533547384.666, "dur": 10.532, + "args": { + "External id": 1413944,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533547389.633, "dur": 5.187, + "args": { + "External id": 1413945,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547392.804, "dur": 0.707, + "args": { + "External id": 1413946,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533547401.524, "dur": 50.339, + "args": { + "External id": 1413947,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547403.345, "dur": 2.646, + "args": { + "External id": 1413948,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547407.430, "dur": 0.713, + "args": { + "External id": 1413949,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547409.561, "dur": 0.556, + "args": { + "External id": 1413950,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547413.813, "dur": 17.464, + "args": { + "External id": 1413951,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547433.803, "dur": 0.771, + "args": { + "External id": 1413952,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547435.671, "dur": 0.595, + "args": { + "External id": 1413953,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547439.878, "dur": 0.793, + "args": { + "External id": 1413954,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547441.841, "dur": 0.385, + "args": { + "External id": 1413955,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533547443.618, "dur": 2.237, + "args": { + "External id": 1413956,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533547469.776, "dur": 36.840, + "args": { + "External id": 1413957,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533547570.939, "dur": 361.434, + "args": { + "External id": 1413958,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533547602.908, "dur": 324.495, + "args": { + "External id": 1413959,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16779, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533547613.237, "dur": 308.629, + "args": { + "External id": 1413960,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533547955.879, "dur": 2.085, + "args": { + "External id": 1413961,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 16781, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338710, "tid": 2338710, + "ts": 6410533548047.046, "dur": 28431.619, + "args": { + "External id": 1413962,"Record function id": 0, "Ev Idx": 16782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548197.429, "dur": 7.097, + "args": { + "External id": 1413963,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548207.800, "dur": 1.367, + "args": { + "External id": 1413964,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548210.849, "dur": 3.859, + "args": { + "External id": 1413965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548216.603, "dur": 1.217, + "args": { + "External id": 1413966,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548219.499, "dur": 1.064, + "args": { + "External id": 1413967,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548221.951, "dur": 1.208, + "args": { + "External id": 1413968,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548226.839, "dur": 1.140, + "args": { + "External id": 1413969,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548229.429, "dur": 2.843, + "args": { + "External id": 1413970,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548233.915, "dur": 0.877, + "args": { + "External id": 1413971,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533548236.078, "dur": 0.794, + "args": { + "External id": 1413972,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533548258.462, "dur": 28144.312, + "args": { + "External id": 1413973,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533548275.195, "dur": 28114.107, + "args": { + "External id": 1413974,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533548294.549, "dur": 17.335, + "args": { + "External id": 1413975,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533548315.466, "dur": 28027.645, + "args": { + "External id": 1413976,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533548318.040, "dur": 28023.848, + "args": { + "External id": 1413977,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533548324.646, "dur": 7.561, + "args": { + "External id": 1413978,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533548333.933, "dur": 28002.222, + "args": { + "External id": 1413979,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533576642.378, "dur": 39.287, + "args": { + "External id": 1413980,"Sequence number": 15109078, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16800 + } + }, + { + "ph": "s", "id": 441, "pid": 2338710, "tid": 2338710, "ts": 6410533576642.378, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533576664.224, "dur": 11.993, + "args": { + "External id": 1413981,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533576669.204, "dur": 6.743, + "args": { + "External id": 1413982,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533576748.096, "dur": 73.025, + "args": { + "External id": 1413983,"Record function id": 0, "Ev Idx": 16803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533576822.419, "dur": 1148.317, + "args": { + "External id": 1413984,"Record function id": 0, "Ev Idx": 16804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533576864.034, "dur": 1093.462, + "args": { + "External id": 1413985,"Sequence number": 15109079, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16805 + } + }, + { + "ph": "s", "id": 440, "pid": 2338710, "tid": 2338710, "ts": 6410533576864.034, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533576934.345, "dur": 52.116, + "args": { + "External id": 1413986,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533577004.212, "dur": 134.093, + "args": { + "External id": 1413987,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533577155.315, "dur": 42.982, + "args": { + "External id": 1413988,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533577208.441, "dur": 30.060, + "args": { + "External id": 1413989,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533577269.861, "dur": 26.408, + "args": { + "External id": 1413990,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533577320.040, "dur": 16.273, + "args": { + "External id": 1413991,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533577362.944, "dur": 152.215, + "args": { + "External id": 1413992,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533577412.863, "dur": 27.581, + "args": { + "External id": 1413993,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533577432.778, "dur": 6.557, + "args": { + "External id": 1413994,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533577443.209, "dur": 4.377, + "args": { + "External id": 1413995,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533577448.769, "dur": 1.490, + "args": { + "External id": 1413996,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533577452.837, "dur": 5.972, + "args": { + "External id": 1413997,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533577526.710, "dur": 54.599, + "args": { + "External id": 1413998,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533577617.408, "dur": 32.937, + "args": { + "External id": 1413999,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533577660.850, "dur": 42.475, + "args": { + "External id": 1414000,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533577712.042, "dur": 34.845, + "args": { + "External id": 1414001,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533577767.894, "dur": 34.070, + "args": { + "External id": 1414002,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533577810.387, "dur": 37.462, + "args": { + "External id": 1414003,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533577866.718, "dur": 19.356, + "args": { + "External id": 1414004,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16824 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.3)", "pid": 2338710, "tid": 2338710, + "ts": 6410533578037.603, "dur": 120.527, + "args": { + "External id": 1414005,"Record function id": 0, "Ev Idx": 16825 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533578237.798, "dur": 50.073, + "args": { + "External id": 1414006,"Record function id": 0, "Ev Idx": 16826 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 2338710, "tid": 2338710, + "ts": 6410533578297.503, "dur": 29407.014, + "args": { + "External id": 1414007,"Record function id": 0, "Ev Idx": 16827 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338710, "tid": 2338710, + "ts": 6410533578307.629, "dur": 1021.026, + "args": { + "External id": 1414008,"Record function id": 0, "Ev Idx": 16828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533578398.945, "dur": 9.698, + "args": { + "External id": 1414009,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533578441.789, "dur": 38.760, + "args": { + "External id": 1414010,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578447.224, "dur": 2.587, + "args": { + "External id": 1414011,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578454.740, "dur": 0.443, + "args": { + "External id": 1414012,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578456.343, "dur": 0.471, + "args": { + "External id": 1414013,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578457.677, "dur": 0.610, + "args": { + "External id": 1414014,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578462.153, "dur": 0.472, + "args": { + "External id": 1414015,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578463.491, "dur": 0.474, + "args": { + "External id": 1414016,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578465.013, "dur": 5.092, + "args": { + "External id": 1414017,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578471.139, "dur": 0.511, + "args": { + "External id": 1414018,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578472.287, "dur": 0.471, + "args": { + "External id": 1414019,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533578493.828, "dur": 59.528, + "args": { + "External id": 1414020,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533578592.418, "dur": 127.835, + "args": { + "External id": 1414021,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533578603.874, "dur": 7.470, + "args": { + "External id": 1414022,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533578616.826, "dur": 10.778, + "args": { + "External id": 1414023,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533578621.521, "dur": 5.671, + "args": { + "External id": 1414024,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578625.030, "dur": 0.669, + "args": { + "External id": 1414025,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533578633.964, "dur": 27.274, + "args": { + "External id": 1414026,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578635.751, "dur": 0.429, + "args": { + "External id": 1414027,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578637.230, "dur": 2.406, + "args": { + "External id": 1414028,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578640.546, "dur": 0.453, + "args": { + "External id": 1414029,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578641.751, "dur": 2.816, + "args": { + "External id": 1414030,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578648.232, "dur": 0.412, + "args": { + "External id": 1414031,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578649.747, "dur": 0.468, + "args": { + "External id": 1414032,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578651.038, "dur": 0.286, + "args": { + "External id": 1414033,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578653.830, "dur": 0.372, + "args": { + "External id": 1414034,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533578655.032, "dur": 0.393, + "args": { + "External id": 1414035,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533578675.471, "dur": 36.444, + "args": { + "External id": 1414036,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533578778.290, "dur": 436.153, + "args": { + "External id": 1414037,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533578809.350, "dur": 399.162, + "args": { + "External id": 1414038,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16858, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533578819.847, "dur": 382.089, + "args": { + "External id": 1414039,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533579245.273, "dur": 2.448, + "args": { + "External id": 1414040,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 16860, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338710, "tid": 2338710, + "ts": 6410533579349.766, "dur": 28132.389, + "args": { + "External id": 1414041,"Record function id": 0, "Ev Idx": 16861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579476.360, "dur": 7.621, + "args": { + "External id": 1414042,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579487.761, "dur": 1.109, + "args": { + "External id": 1414043,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579490.634, "dur": 2.912, + "args": { + "External id": 1414044,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579495.242, "dur": 0.826, + "args": { + "External id": 1414045,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579497.493, "dur": 0.988, + "args": { + "External id": 1414046,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579499.628, "dur": 1.138, + "args": { + "External id": 1414047,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579504.803, "dur": 1.292, + "args": { + "External id": 1414048,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579507.499, "dur": 3.080, + "args": { + "External id": 1414049,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579511.866, "dur": 0.820, + "args": { + "External id": 1414050,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533579514.032, "dur": 1.061, + "args": { + "External id": 1414051,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533579535.666, "dur": 27874.542, + "args": { + "External id": 1414052,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533579551.407, "dur": 27847.277, + "args": { + "External id": 1414053,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533579569.086, "dur": 17.606, + "args": { + "External id": 1414054,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533579590.175, "dur": 27765.034, + "args": { + "External id": 1414055,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533579593.006, "dur": 27761.201, + "args": { + "External id": 1414056,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533579599.100, "dur": 7.633, + "args": { + "External id": 1414057,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533579608.388, "dur": 27741.255, + "args": { + "External id": 1414058,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533607642.152, "dur": 36.445, + "args": { + "External id": 1414059,"Sequence number": 15109080, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16879 + } + }, + { + "ph": "s", "id": 439, "pid": 2338710, "tid": 2338710, "ts": 6410533607642.152, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533607661.902, "dur": 11.830, + "args": { + "External id": 1414060,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533607666.744, "dur": 6.728, + "args": { + "External id": 1414061,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533607746.561, "dur": 75.711, + "args": { + "External id": 1414062,"Record function id": 0, "Ev Idx": 16882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533607823.753, "dur": 1143.969, + "args": { + "External id": 1414063,"Record function id": 0, "Ev Idx": 16883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533607864.004, "dur": 1089.152, + "args": { + "External id": 1414064,"Sequence number": 15109081, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16884 + } + }, + { + "ph": "s", "id": 438, "pid": 2338710, "tid": 2338710, "ts": 6410533607864.004, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533607931.282, "dur": 51.277, + "args": { + "External id": 1414065,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533607995.377, "dur": 135.169, + "args": { + "External id": 1414066,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533608145.891, "dur": 43.485, + "args": { + "External id": 1414067,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533608198.966, "dur": 29.610, + "args": { + "External id": 1414068,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533608257.442, "dur": 30.359, + "args": { + "External id": 1414069,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533608309.780, "dur": 17.166, + "args": { + "External id": 1414070,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533608352.323, "dur": 158.007, + "args": { + "External id": 1414071,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533608404.638, "dur": 28.403, + "args": { + "External id": 1414072,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533608410.035, "dur": 21.984, + "args": { + "External id": 1414073,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533608436.349, "dur": 4.688, + "args": { + "External id": 1414074,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533608442.145, "dur": 1.357, + "args": { + "External id": 1414075,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533608446.002, "dur": 6.858, + "args": { + "External id": 1414076,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533608522.049, "dur": 57.037, + "args": { + "External id": 1414077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533608613.420, "dur": 31.270, + "args": { + "External id": 1414078,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533608655.098, "dur": 43.681, + "args": { + "External id": 1414079,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533608708.286, "dur": 35.336, + "args": { + "External id": 1414080,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533608768.024, "dur": 26.169, + "args": { + "External id": 1414081,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533608802.504, "dur": 36.131, + "args": { + "External id": 1414082,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533608857.958, "dur": 18.471, + "args": { + "External id": 1414083,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16903 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.4)", "pid": 2338710, "tid": 2338710, + "ts": 6410533609035.435, "dur": 122.024, + "args": { + "External id": 1414084,"Record function id": 0, "Ev Idx": 16904 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533609236.918, "dur": 50.135, + "args": { + "External id": 1414085,"Record function id": 0, "Ev Idx": 16905 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 2338710, "tid": 2338710, + "ts": 6410533609296.102, "dur": 30857.612, + "args": { + "External id": 1414086,"Record function id": 0, "Ev Idx": 16906 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338710, "tid": 2338710, + "ts": 6410533609305.282, "dur": 966.600, + "args": { + "External id": 1414087,"Record function id": 0, "Ev Idx": 16907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533609393.057, "dur": 9.508, + "args": { + "External id": 1414088,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533609430.817, "dur": 44.400, + "args": { + "External id": 1414089,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609436.479, "dur": 2.513, + "args": { + "External id": 1414090,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609443.656, "dur": 0.354, + "args": { + "External id": 1414091,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609445.176, "dur": 0.459, + "args": { + "External id": 1414092,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609446.556, "dur": 0.714, + "args": { + "External id": 1414093,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609450.531, "dur": 0.871, + "args": { + "External id": 1414094,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609452.488, "dur": 0.638, + "args": { + "External id": 1414095,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609454.346, "dur": 4.383, + "args": { + "External id": 1414096,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609459.839, "dur": 0.327, + "args": { + "External id": 1414097,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609465.993, "dur": 0.447, + "args": { + "External id": 1414098,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533609489.205, "dur": 54.611, + "args": { + "External id": 1414099,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533609579.613, "dur": 134.903, + "args": { + "External id": 1414100,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533609591.207, "dur": 5.038, + "args": { + "External id": 1414101,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533609601.580, "dur": 14.643, + "args": { + "External id": 1414102,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533609608.653, "dur": 7.139, + "args": { + "External id": 1414103,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609611.805, "dur": 2.620, + "args": { + "External id": 1414104,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533609623.289, "dur": 32.663, + "args": { + "External id": 1414105,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609625.007, "dur": 0.575, + "args": { + "External id": 1414106,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609626.808, "dur": 0.650, + "args": { + "External id": 1414107,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609628.524, "dur": 0.406, + "args": { + "External id": 1414108,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609632.306, "dur": 3.237, + "args": { + "External id": 1414109,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609636.462, "dur": 0.346, + "args": { + "External id": 1414110,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609637.770, "dur": 2.776, + "args": { + "External id": 1414111,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609641.405, "dur": 0.593, + "args": { + "External id": 1414112,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609642.856, "dur": 0.409, + "args": { + "External id": 1414113,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533609646.411, "dur": 0.495, + "args": { + "External id": 1414114,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533609669.982, "dur": 32.112, + "args": { + "External id": 1414115,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533609770.485, "dur": 397.779, + "args": { + "External id": 1414116,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533609802.000, "dur": 360.498, + "args": { + "External id": 1414117,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16937, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533609812.069, "dur": 343.930, + "args": { + "External id": 1414118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533610194.946, "dur": 2.327, + "args": { + "External id": 1414119,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 16939, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338710, "tid": 2338710, + "ts": 6410533610292.335, "dur": 29596.875, + "args": { + "External id": 1414120,"Record function id": 0, "Ev Idx": 16940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610397.280, "dur": 6.694, + "args": { + "External id": 1414121,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610407.982, "dur": 1.044, + "args": { + "External id": 1414122,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610410.862, "dur": 17.900, + "args": { + "External id": 1414123,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610433.648, "dur": 1.563, + "args": { + "External id": 1414124,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610436.813, "dur": 1.146, + "args": { + "External id": 1414125,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610441.493, "dur": 1.265, + "args": { + "External id": 1414126,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610444.509, "dur": 1.192, + "args": { + "External id": 1414127,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610447.024, "dur": 2.956, + "args": { + "External id": 1414128,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610451.409, "dur": 1.444, + "args": { + "External id": 1414129,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533610456.749, "dur": 0.903, + "args": { + "External id": 1414130,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533610476.778, "dur": 29348.020, + "args": { + "External id": 1414131,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533610492.185, "dur": 29320.694, + "args": { + "External id": 1414132,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533610509.313, "dur": 17.703, + "args": { + "External id": 1414133,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533610530.727, "dur": 29237.216, + "args": { + "External id": 1414134,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533610533.198, "dur": 29233.659, + "args": { + "External id": 1414135,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533610539.441, "dur": 7.645, + "args": { + "External id": 1414136,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533610548.949, "dur": 29212.547, + "args": { + "External id": 1414137,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533640081.506, "dur": 40.531, + "args": { + "External id": 1414138,"Sequence number": 15109082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16958 + } + }, + { + "ph": "s", "id": 437, "pid": 2338710, "tid": 2338710, "ts": 6410533640081.506, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533640104.370, "dur": 12.307, + "args": { + "External id": 1414139,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533640109.679, "dur": 6.653, + "args": { + "External id": 1414140,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533640196.677, "dur": 72.793, + "args": { + "External id": 1414141,"Record function id": 0, "Ev Idx": 16961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533640271.124, "dur": 1267.610, + "args": { + "External id": 1414142,"Record function id": 0, "Ev Idx": 16962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533640314.650, "dur": 1208.036, + "args": { + "External id": 1414143,"Sequence number": 15109083, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16963 + } + }, + { + "ph": "s", "id": 436, "pid": 2338710, "tid": 2338710, "ts": 6410533640314.650, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533640388.749, "dur": 67.774, + "args": { + "External id": 1414144,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533640503.965, "dur": 100.880, + "args": { + "External id": 1414145,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533640617.312, "dur": 37.878, + "args": { + "External id": 1414146,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533640664.659, "dur": 29.838, + "args": { + "External id": 1414147,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533640724.971, "dur": 29.284, + "args": { + "External id": 1414148,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533640777.375, "dur": 19.621, + "args": { + "External id": 1414149,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533640821.413, "dur": 135.006, + "args": { + "External id": 1414150,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533640873.047, "dur": 11.125, + "args": { + "External id": 1414151,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533640878.348, "dur": 5.010, + "args": { + "External id": 1414152,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533640886.656, "dur": 4.497, + "args": { + "External id": 1414153,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533640892.354, "dur": 1.314, + "args": { + "External id": 1414154,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533640896.014, "dur": 8.907, + "args": { + "External id": 1414155,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533640967.463, "dur": 58.808, + "args": { + "External id": 1414156,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533641103.490, "dur": 52.169, + "args": { + "External id": 1414157,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533641176.290, "dur": 62.191, + "args": { + "External id": 1414158,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533641246.497, "dur": 36.577, + "args": { + "External id": 1414159,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533641310.731, "dur": 31.223, + "args": { + "External id": 1414160,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533641350.467, "dur": 37.832, + "args": { + "External id": 1414161,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533641408.279, "dur": 34.839, + "args": { + "External id": 1414162,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16982 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.5)", "pid": 2338710, "tid": 2338710, + "ts": 6410533641610.147, "dur": 83.219, + "args": { + "External id": 1414163,"Record function id": 0, "Ev Idx": 16983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533641772.228, "dur": 52.420, + "args": { + "External id": 1414164,"Record function id": 0, "Ev Idx": 16984 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 2338710, "tid": 2338710, + "ts": 6410533641834.648, "dur": 30050.199, + "args": { + "External id": 1414165,"Record function id": 0, "Ev Idx": 16985 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338710, "tid": 2338710, + "ts": 6410533641842.346, "dur": 966.001, + "args": { + "External id": 1414166,"Record function id": 0, "Ev Idx": 16986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533641930.075, "dur": 10.393, + "args": { + "External id": 1414167,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533641953.440, "dur": 40.530, + "args": { + "External id": 1414168,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641958.944, "dur": 2.234, + "args": { + "External id": 1414169,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641965.298, "dur": 0.496, + "args": { + "External id": 1414170,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641966.695, "dur": 0.334, + "args": { + "External id": 1414171,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641967.765, "dur": 0.538, + "args": { + "External id": 1414172,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641971.954, "dur": 0.566, + "args": { + "External id": 1414173,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641976.790, "dur": 0.524, + "args": { + "External id": 1414174,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641978.121, "dur": 5.083, + "args": { + "External id": 1414175,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641983.971, "dur": 0.426, + "args": { + "External id": 1414176,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533641985.080, "dur": 0.293, + "args": { + "External id": 1414177,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533642004.850, "dur": 85.629, + "args": { + "External id": 1414178,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533642129.255, "dur": 139.697, + "args": { + "External id": 1414179,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533642141.409, "dur": 7.881, + "args": { + "External id": 1414180,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533642154.876, "dur": 13.828, + "args": { + "External id": 1414181,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533642161.783, "dur": 6.528, + "args": { + "External id": 1414182,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642165.555, "dur": 0.857, + "args": { + "External id": 1414183,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533642176.505, "dur": 36.767, + "args": { + "External id": 1414184,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642179.032, "dur": 2.505, + "args": { + "External id": 1414185,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642183.431, "dur": 0.530, + "args": { + "External id": 1414186,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642185.955, "dur": 0.614, + "args": { + "External id": 1414187,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642189.814, "dur": 2.613, + "args": { + "External id": 1414188,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642193.756, "dur": 0.526, + "args": { + "External id": 1414189,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642195.529, "dur": 0.560, + "args": { + "External id": 1414190,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642200.559, "dur": 0.351, + "args": { + "External id": 1414191,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642202.091, "dur": 0.857, + "args": { + "External id": 1414192,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533642204.366, "dur": 2.751, + "args": { + "External id": 1414193,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533642225.599, "dur": 35.298, + "args": { + "External id": 1414194,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533642326.120, "dur": 377.840, + "args": { + "External id": 1414195,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533642357.590, "dur": 341.005, + "args": { + "External id": 1414196,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17016, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533642368.068, "dur": 324.320, + "args": { + "External id": 1414197,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533642731.350, "dur": 2.487, + "args": { + "External id": 1414198,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17018, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338710, "tid": 2338710, + "ts": 6410533642829.967, "dur": 28832.988, + "args": { + "External id": 1414199,"Record function id": 0, "Ev Idx": 17019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642936.283, "dur": 6.857, + "args": { + "External id": 1414200,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642946.947, "dur": 1.512, + "args": { + "External id": 1414201,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642950.076, "dur": 3.552, + "args": { + "External id": 1414202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642955.303, "dur": 1.198, + "args": { + "External id": 1414203,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642958.295, "dur": 1.145, + "args": { + "External id": 1414204,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642960.888, "dur": 1.209, + "args": { + "External id": 1414205,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642965.699, "dur": 1.299, + "args": { + "External id": 1414206,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642968.488, "dur": 2.875, + "args": { + "External id": 1414207,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642972.970, "dur": 0.728, + "args": { + "External id": 1414208,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533642975.019, "dur": 5.878, + "args": { + "External id": 1414209,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533643001.266, "dur": 28600.074, + "args": { + "External id": 1414210,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533643017.050, "dur": 28572.277, + "args": { + "External id": 1414211,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533643036.944, "dur": 51.354, + "args": { + "External id": 1414212,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533643093.026, "dur": 28450.483, + "args": { + "External id": 1414213,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533643095.804, "dur": 28446.616, + "args": { + "External id": 1414214,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533643102.303, "dur": 6.994, + "args": { + "External id": 1414215,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533643111.238, "dur": 28426.767, + "args": { + "External id": 1414216,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533671822.235, "dur": 37.187, + "args": { + "External id": 1414217,"Sequence number": 15109084, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17037 + } + }, + { + "ph": "s", "id": 435, "pid": 2338710, "tid": 2338710, "ts": 6410533671822.235, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533671842.546, "dur": 12.167, + "args": { + "External id": 1414218,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533671848.218, "dur": 6.265, + "args": { + "External id": 1414219,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533671924.406, "dur": 76.218, + "args": { + "External id": 1414220,"Record function id": 0, "Ev Idx": 17040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533672002.311, "dur": 1185.187, + "args": { + "External id": 1414221,"Record function id": 0, "Ev Idx": 17041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533672043.472, "dur": 1130.253, + "args": { + "External id": 1414222,"Sequence number": 15109085, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17042 + } + }, + { + "ph": "s", "id": 434, "pid": 2338710, "tid": 2338710, "ts": 6410533672043.472, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533672145.969, "dur": 60.457, + "args": { + "External id": 1414223,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533672220.556, "dur": 106.618, + "args": { + "External id": 1414224,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533672341.215, "dur": 40.600, + "args": { + "External id": 1414225,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533672392.749, "dur": 46.605, + "args": { + "External id": 1414226,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533672470.954, "dur": 29.863, + "args": { + "External id": 1414227,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533672523.209, "dur": 20.039, + "args": { + "External id": 1414228,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533672567.197, "dur": 136.384, + "args": { + "External id": 1414229,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533672621.727, "dur": 12.248, + "args": { + "External id": 1414230,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533672627.574, "dur": 5.548, + "args": { + "External id": 1414231,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533672636.569, "dur": 4.005, + "args": { + "External id": 1414232,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533672641.804, "dur": 0.845, + "args": { + "External id": 1414233,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533672645.362, "dur": 5.424, + "args": { + "External id": 1414234,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533672714.051, "dur": 54.602, + "args": { + "External id": 1414235,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533672801.527, "dur": 31.141, + "args": { + "External id": 1414236,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533672845.447, "dur": 43.766, + "args": { + "External id": 1414237,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533672897.806, "dur": 35.332, + "args": { + "External id": 1414238,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533672955.049, "dur": 27.030, + "args": { + "External id": 1414239,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533672990.182, "dur": 36.247, + "args": { + "External id": 1414240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533673046.213, "dur": 54.230, + "args": { + "External id": 1414241,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17061 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.6)", "pid": 2338710, "tid": 2338710, + "ts": 6410533673254.519, "dur": 78.023, + "args": { + "External id": 1414242,"Record function id": 0, "Ev Idx": 17062 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533673407.447, "dur": 89.698, + "args": { + "External id": 1414243,"Record function id": 0, "Ev Idx": 17063 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 2338710, "tid": 2338710, + "ts": 6410533673510.556, "dur": 30959.597, + "args": { + "External id": 1414244,"Record function id": 0, "Ev Idx": 17064 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338710, "tid": 2338710, + "ts": 6410533673519.632, "dur": 963.482, + "args": { + "External id": 1414245,"Record function id": 0, "Ev Idx": 17065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533673606.533, "dur": 11.317, + "args": { + "External id": 1414246,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533673632.276, "dur": 38.699, + "args": { + "External id": 1414247,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673637.713, "dur": 2.517, + "args": { + "External id": 1414248,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673644.031, "dur": 0.589, + "args": { + "External id": 1414249,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673645.459, "dur": 0.677, + "args": { + "External id": 1414250,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673647.396, "dur": 0.554, + "args": { + "External id": 1414251,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673651.220, "dur": 0.622, + "args": { + "External id": 1414252,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673653.392, "dur": 0.475, + "args": { + "External id": 1414253,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673654.814, "dur": 4.989, + "args": { + "External id": 1414254,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673661.163, "dur": 0.235, + "args": { + "External id": 1414255,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673662.636, "dur": 0.370, + "args": { + "External id": 1414256,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533673683.126, "dur": 55.348, + "args": { + "External id": 1414257,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533673777.751, "dur": 131.920, + "args": { + "External id": 1414258,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533673789.188, "dur": 5.630, + "args": { + "External id": 1414259,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533673800.433, "dur": 13.545, + "args": { + "External id": 1414260,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533673807.651, "dur": 5.897, + "args": { + "External id": 1414261,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673811.690, "dur": 0.438, + "args": { + "External id": 1414262,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533673820.693, "dur": 32.035, + "args": { + "External id": 1414263,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673822.709, "dur": 0.562, + "args": { + "External id": 1414264,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673825.330, "dur": 2.538, + "args": { + "External id": 1414265,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673829.170, "dur": 0.411, + "args": { + "External id": 1414266,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673831.476, "dur": 2.691, + "args": { + "External id": 1414267,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673837.880, "dur": 0.281, + "args": { + "External id": 1414268,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673839.526, "dur": 0.321, + "args": { + "External id": 1414269,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673840.706, "dur": 0.550, + "args": { + "External id": 1414270,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673845.817, "dur": 0.423, + "args": { + "External id": 1414271,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533673847.438, "dur": 0.557, + "args": { + "External id": 1414272,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533673866.687, "dur": 34.577, + "args": { + "External id": 1414273,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533673964.085, "dur": 398.429, + "args": { + "External id": 1414274,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533673996.262, "dur": 360.819, + "args": { + "External id": 1414275,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17095, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533674006.237, "dur": 344.557, + "args": { + "External id": 1414276,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533674388.841, "dur": 2.657, + "args": { + "External id": 1414277,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17097, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338710, "tid": 2338710, + "ts": 6410533674505.276, "dur": 29727.406, + "args": { + "External id": 1414278,"Record function id": 0, "Ev Idx": 17098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674609.785, "dur": 7.021, + "args": { + "External id": 1414279,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674620.469, "dur": 1.101, + "args": { + "External id": 1414280,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674623.195, "dur": 3.181, + "args": { + "External id": 1414281,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674628.236, "dur": 1.063, + "args": { + "External id": 1414282,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674630.792, "dur": 0.984, + "args": { + "External id": 1414283,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674632.962, "dur": 1.145, + "args": { + "External id": 1414284,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674637.575, "dur": 0.826, + "args": { + "External id": 1414285,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674639.979, "dur": 2.326, + "args": { + "External id": 1414286,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674643.863, "dur": 1.029, + "args": { + "External id": 1414287,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533674646.541, "dur": 0.780, + "args": { + "External id": 1414288,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533674667.969, "dur": 29499.693, + "args": { + "External id": 1414289,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533674683.832, "dur": 29470.877, + "args": { + "External id": 1414290,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533674703.706, "dur": 16.204, + "args": { + "External id": 1414291,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533674723.385, "dur": 29386.569, + "args": { + "External id": 1414292,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533674725.923, "dur": 29382.970, + "args": { + "External id": 1414293,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533674731.972, "dur": 5.474, + "args": { + "External id": 1414294,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533674739.150, "dur": 29364.872, + "args": { + "External id": 1414295,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533704393.297, "dur": 48.011, + "args": { + "External id": 1414296,"Sequence number": 15109086, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17116 + } + }, + { + "ph": "s", "id": 433, "pid": 2338710, "tid": 2338710, "ts": 6410533704393.297, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533704411.944, "dur": 23.760, + "args": { + "External id": 1414297,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533704428.622, "dur": 6.682, + "args": { + "External id": 1414298,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533704510.783, "dur": 70.886, + "args": { + "External id": 1414299,"Record function id": 0, "Ev Idx": 17119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533704583.124, "dur": 1175.634, + "args": { + "External id": 1414300,"Record function id": 0, "Ev Idx": 17120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533704624.444, "dur": 1120.842, + "args": { + "External id": 1414301,"Sequence number": 15109087, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17121 + } + }, + { + "ph": "s", "id": 432, "pid": 2338710, "tid": 2338710, "ts": 6410533704624.444, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533704694.254, "dur": 52.567, + "args": { + "External id": 1414302,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533704760.105, "dur": 107.934, + "args": { + "External id": 1414303,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533704882.320, "dur": 40.391, + "args": { + "External id": 1414304,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533704932.162, "dur": 30.897, + "args": { + "External id": 1414305,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533704989.665, "dur": 36.527, + "args": { + "External id": 1414306,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533705045.439, "dur": 58.205, + "args": { + "External id": 1414307,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533705131.165, "dur": 147.178, + "args": { + "External id": 1414308,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533705188.702, "dur": 12.662, + "args": { + "External id": 1414309,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533705194.441, "dur": 6.152, + "args": { + "External id": 1414310,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533705203.644, "dur": 4.231, + "args": { + "External id": 1414311,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533705209.178, "dur": 0.934, + "args": { + "External id": 1414312,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533705214.932, "dur": 6.865, + "args": { + "External id": 1414313,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533705288.929, "dur": 55.586, + "args": { + "External id": 1414314,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533705379.977, "dur": 30.783, + "args": { + "External id": 1414315,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533705438.658, "dur": 49.308, + "args": { + "External id": 1414316,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533705498.339, "dur": 35.805, + "args": { + "External id": 1414317,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533705564.032, "dur": 30.023, + "args": { + "External id": 1414318,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533705599.649, "dur": 36.924, + "args": { + "External id": 1414319,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533705655.926, "dur": 21.506, + "args": { + "External id": 1414320,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17140 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.7)", "pid": 2338710, "tid": 2338710, + "ts": 6410533705823.380, "dur": 77.951, + "args": { + "External id": 1414321,"Record function id": 0, "Ev Idx": 17141 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533705976.273, "dur": 46.614, + "args": { + "External id": 1414322,"Record function id": 0, "Ev Idx": 17142 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 2338710, "tid": 2338710, + "ts": 6410533706031.844, "dur": 29990.775, + "args": { + "External id": 1414323,"Record function id": 0, "Ev Idx": 17143 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338710, "tid": 2338710, + "ts": 6410533706039.360, "dur": 878.044, + "args": { + "External id": 1414324,"Record function id": 0, "Ev Idx": 17144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533706164.615, "dur": 9.495, + "args": { + "External id": 1414325,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533706188.630, "dur": 38.677, + "args": { + "External id": 1414326,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706194.844, "dur": 2.115, + "args": { + "External id": 1414327,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706201.094, "dur": 0.635, + "args": { + "External id": 1414328,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706203.164, "dur": 0.376, + "args": { + "External id": 1414329,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706205.284, "dur": 0.606, + "args": { + "External id": 1414330,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706209.588, "dur": 0.545, + "args": { + "External id": 1414331,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706211.431, "dur": 0.403, + "args": { + "External id": 1414332,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706213.340, "dur": 3.909, + "args": { + "External id": 1414333,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706218.336, "dur": 0.551, + "args": { + "External id": 1414334,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706220.272, "dur": 0.510, + "args": { + "External id": 1414335,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533706239.318, "dur": 54.200, + "args": { + "External id": 1414336,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533706327.891, "dur": 147.051, + "args": { + "External id": 1414337,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533706339.261, "dur": 3.773, + "args": { + "External id": 1414338,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533706350.456, "dur": 10.447, + "args": { + "External id": 1414339,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533706355.387, "dur": 5.093, + "args": { + "External id": 1414340,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706358.549, "dur": 0.515, + "args": { + "External id": 1414341,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533706367.796, "dur": 32.906, + "args": { + "External id": 1414342,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706370.434, "dur": 2.570, + "args": { + "External id": 1414343,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706374.511, "dur": 0.566, + "args": { + "External id": 1414344,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706376.742, "dur": 0.474, + "args": { + "External id": 1414345,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706380.577, "dur": 2.226, + "args": { + "External id": 1414346,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706384.611, "dur": 0.493, + "args": { + "External id": 1414347,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706386.515, "dur": 0.461, + "args": { + "External id": 1414348,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706390.684, "dur": 0.347, + "args": { + "External id": 1414349,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706392.147, "dur": 0.532, + "args": { + "External id": 1414350,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533706394.147, "dur": 2.507, + "args": { + "External id": 1414351,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533706412.414, "dur": 53.061, + "args": { + "External id": 1414352,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533706532.602, "dur": 292.168, + "args": { + "External id": 1414353,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533706567.754, "dur": 251.976, + "args": { + "External id": 1414354,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17174, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533706578.176, "dur": 235.666, + "args": { + "External id": 1414355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533706846.925, "dur": 2.438, + "args": { + "External id": 1414356,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17176, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338710, "tid": 2338710, + "ts": 6410533706937.652, "dur": 28863.882, + "args": { + "External id": 1414357,"Record function id": 0, "Ev Idx": 17177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707037.855, "dur": 5.694, + "args": { + "External id": 1414358,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707046.884, "dur": 1.054, + "args": { + "External id": 1414359,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707049.698, "dur": 40.397, + "args": { + "External id": 1414360,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707094.466, "dur": 1.321, + "args": { + "External id": 1414361,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707097.140, "dur": 1.076, + "args": { + "External id": 1414362,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707099.440, "dur": 0.998, + "args": { + "External id": 1414363,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707104.794, "dur": 0.904, + "args": { + "External id": 1414364,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707107.349, "dur": 2.192, + "args": { + "External id": 1414365,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707111.020, "dur": 0.856, + "args": { + "External id": 1414366,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533707113.244, "dur": 0.888, + "args": { + "External id": 1414367,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533707136.066, "dur": 28601.835, + "args": { + "External id": 1414368,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533707152.068, "dur": 28573.190, + "args": { + "External id": 1414369,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533707169.137, "dur": 16.805, + "args": { + "External id": 1414370,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533707189.381, "dur": 28493.192, + "args": { + "External id": 1414371,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533707191.849, "dur": 28489.689, + "args": { + "External id": 1414372,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533707198.236, "dur": 6.267, + "args": { + "External id": 1414373,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533707206.263, "dur": 28470.767, + "args": { + "External id": 1414374,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533735961.261, "dur": 35.431, + "args": { + "External id": 1414375,"Sequence number": 15109088, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17195 + } + }, + { + "ph": "s", "id": 431, "pid": 2338710, "tid": 2338710, "ts": 6410533735961.261, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533735980.367, "dur": 11.216, + "args": { + "External id": 1414376,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533735985.318, "dur": 5.982, + "args": { + "External id": 1414377,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533736091.925, "dur": 76.347, + "args": { + "External id": 1414378,"Record function id": 0, "Ev Idx": 17198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533736170.339, "dur": 1144.455, + "args": { + "External id": 1414379,"Record function id": 0, "Ev Idx": 17199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533736214.199, "dur": 1087.353, + "args": { + "External id": 1414380,"Sequence number": 15109089, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17200 + } + }, + { + "ph": "s", "id": 430, "pid": 2338710, "tid": 2338710, "ts": 6410533736214.199, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533736285.937, "dur": 52.445, + "args": { + "External id": 1414381,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533736351.679, "dur": 120.831, + "args": { + "External id": 1414382,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533736487.630, "dur": 43.053, + "args": { + "External id": 1414383,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533736541.120, "dur": 30.002, + "args": { + "External id": 1414384,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533736599.902, "dur": 28.598, + "args": { + "External id": 1414385,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533736649.848, "dur": 16.458, + "args": { + "External id": 1414386,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533736690.083, "dur": 132.731, + "args": { + "External id": 1414387,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533736739.577, "dur": 12.444, + "args": { + "External id": 1414388,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533736745.484, "dur": 5.636, + "args": { + "External id": 1414389,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533736754.716, "dur": 4.671, + "args": { + "External id": 1414390,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533736761.090, "dur": 1.410, + "args": { + "External id": 1414391,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533736764.827, "dur": 6.850, + "args": { + "External id": 1414392,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533736833.367, "dur": 51.251, + "args": { + "External id": 1414393,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533736916.433, "dur": 30.530, + "args": { + "External id": 1414394,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533736958.734, "dur": 44.835, + "args": { + "External id": 1414395,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533737013.006, "dur": 35.981, + "args": { + "External id": 1414396,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533737112.784, "dur": 28.523, + "args": { + "External id": 1414397,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533737150.955, "dur": 41.431, + "args": { + "External id": 1414398,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533737211.953, "dur": 19.981, + "args": { + "External id": 1414399,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17219 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.8)", "pid": 2338710, "tid": 2338710, + "ts": 6410533737381.399, "dur": 94.336, + "args": { + "External id": 1414400,"Record function id": 0, "Ev Idx": 17220 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533737554.592, "dur": 49.942, + "args": { + "External id": 1414401,"Record function id": 0, "Ev Idx": 17221 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 2338710, "tid": 2338710, + "ts": 6410533737614.075, "dur": 30424.366, + "args": { + "External id": 1414402,"Record function id": 0, "Ev Idx": 17222 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338710, "tid": 2338710, + "ts": 6410533737622.957, "dur": 993.680, + "args": { + "External id": 1414403,"Record function id": 0, "Ev Idx": 17223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533737710.327, "dur": 9.685, + "args": { + "External id": 1414404,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533737733.446, "dur": 38.916, + "args": { + "External id": 1414405,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737739.830, "dur": 2.198, + "args": { + "External id": 1414406,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737747.019, "dur": 0.462, + "args": { + "External id": 1414407,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737748.682, "dur": 0.428, + "args": { + "External id": 1414408,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737750.351, "dur": 0.575, + "args": { + "External id": 1414409,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737754.958, "dur": 0.445, + "args": { + "External id": 1414410,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737756.369, "dur": 0.577, + "args": { + "External id": 1414411,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737758.790, "dur": 4.131, + "args": { + "External id": 1414412,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737764.180, "dur": 0.541, + "args": { + "External id": 1414413,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737766.011, "dur": 0.311, + "args": { + "External id": 1414414,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533737784.888, "dur": 55.161, + "args": { + "External id": 1414415,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533737876.478, "dur": 122.198, + "args": { + "External id": 1414416,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533737887.712, "dur": 3.614, + "args": { + "External id": 1414417,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533737896.580, "dur": 10.142, + "args": { + "External id": 1414418,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533737901.133, "dur": 5.205, + "args": { + "External id": 1414419,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737904.562, "dur": 0.462, + "args": { + "External id": 1414420,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533737913.169, "dur": 29.933, + "args": { + "External id": 1414421,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737915.194, "dur": 2.466, + "args": { + "External id": 1414422,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737918.924, "dur": 0.614, + "args": { + "External id": 1414423,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737921.282, "dur": 0.310, + "args": { + "External id": 1414424,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737924.774, "dur": 2.694, + "args": { + "External id": 1414425,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737928.750, "dur": 0.336, + "args": { + "External id": 1414426,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737930.042, "dur": 0.321, + "args": { + "External id": 1414427,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737933.837, "dur": 0.391, + "args": { + "External id": 1414428,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737935.536, "dur": 0.326, + "args": { + "External id": 1414429,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533737936.955, "dur": 1.827, + "args": { + "External id": 1414430,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533737956.651, "dur": 34.331, + "args": { + "External id": 1414431,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533738050.915, "dur": 455.335, + "args": { + "External id": 1414432,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533738120.028, "dur": 380.662, + "args": { + "External id": 1414433,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17253, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533738131.519, "dur": 360.462, + "args": { + "External id": 1414434,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533738534.130, "dur": 2.442, + "args": { + "External id": 1414435,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17255, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338710, "tid": 2338710, + "ts": 6410533738638.044, "dur": 29167.743, + "args": { + "External id": 1414436,"Record function id": 0, "Ev Idx": 17256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738747.596, "dur": 7.241, + "args": { + "External id": 1414437,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738758.049, "dur": 1.063, + "args": { + "External id": 1414438,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738760.714, "dur": 3.202, + "args": { + "External id": 1414439,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738765.828, "dur": 0.647, + "args": { + "External id": 1414440,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738767.755, "dur": 0.911, + "args": { + "External id": 1414441,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738769.874, "dur": 0.997, + "args": { + "External id": 1414442,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738774.324, "dur": 0.755, + "args": { + "External id": 1414443,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738777.127, "dur": 2.304, + "args": { + "External id": 1414444,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738780.933, "dur": 0.679, + "args": { + "External id": 1414445,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533738782.919, "dur": 1.140, + "args": { + "External id": 1414446,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533738804.504, "dur": 28935.499, + "args": { + "External id": 1414447,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533738820.250, "dur": 28908.251, + "args": { + "External id": 1414448,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533738836.562, "dur": 16.654, + "args": { + "External id": 1414449,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533738856.691, "dur": 28823.092, + "args": { + "External id": 1414450,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533738859.428, "dur": 28819.181, + "args": { + "External id": 1414451,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533738866.216, "dur": 5.621, + "args": { + "External id": 1414452,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533738873.762, "dur": 28799.173, + "args": { + "External id": 1414453,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533767972.135, "dur": 39.919, + "args": { + "External id": 1414454,"Sequence number": 15109090, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17274 + } + }, + { + "ph": "s", "id": 429, "pid": 2338710, "tid": 2338710, "ts": 6410533767972.135, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533767995.197, "dur": 11.920, + "args": { + "External id": 1414455,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533768000.463, "dur": 6.400, + "args": { + "External id": 1414456,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533768108.690, "dur": 72.171, + "args": { + "External id": 1414457,"Record function id": 0, "Ev Idx": 17277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533768182.740, "dur": 1166.179, + "args": { + "External id": 1414458,"Record function id": 0, "Ev Idx": 17278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533768226.945, "dur": 1108.231, + "args": { + "External id": 1414459,"Sequence number": 15109091, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17279 + } + }, + { + "ph": "s", "id": 428, "pid": 2338710, "tid": 2338710, "ts": 6410533768226.945, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533768300.425, "dur": 53.496, + "args": { + "External id": 1414460,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533768367.083, "dur": 119.586, + "args": { + "External id": 1414461,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533768501.649, "dur": 42.774, + "args": { + "External id": 1414462,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533768556.834, "dur": 31.520, + "args": { + "External id": 1414463,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533768616.511, "dur": 30.096, + "args": { + "External id": 1414464,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533768667.009, "dur": 16.547, + "args": { + "External id": 1414465,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533768711.092, "dur": 135.818, + "args": { + "External id": 1414466,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533768761.690, "dur": 11.881, + "args": { + "External id": 1414467,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533768766.995, "dur": 5.810, + "args": { + "External id": 1414468,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533768776.341, "dur": 4.555, + "args": { + "External id": 1414469,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533768782.204, "dur": 1.239, + "args": { + "External id": 1414470,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533768785.718, "dur": 6.553, + "args": { + "External id": 1414471,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533768860.173, "dur": 49.621, + "args": { + "External id": 1414472,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533768945.448, "dur": 31.209, + "args": { + "External id": 1414473,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533768989.352, "dur": 42.421, + "args": { + "External id": 1414474,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533769040.797, "dur": 72.239, + "args": { + "External id": 1414475,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533769143.689, "dur": 30.921, + "args": { + "External id": 1414476,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533769181.981, "dur": 40.674, + "args": { + "External id": 1414477,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533769243.457, "dur": 20.005, + "args": { + "External id": 1414478,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17298 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.9)", "pid": 2338710, "tid": 2338710, + "ts": 6410533769427.235, "dur": 84.764, + "args": { + "External id": 1414479,"Record function id": 0, "Ev Idx": 17299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533769592.120, "dur": 49.157, + "args": { + "External id": 1414480,"Record function id": 0, "Ev Idx": 17300 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 2338710, "tid": 2338710, + "ts": 6410533769650.750, "dur": 31705.445, + "args": { + "External id": 1414481,"Record function id": 0, "Ev Idx": 17301 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338710, "tid": 2338710, + "ts": 6410533769659.503, "dur": 950.137, + "args": { + "External id": 1414482,"Record function id": 0, "Ev Idx": 17302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533769747.563, "dur": 9.295, + "args": { + "External id": 1414483,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533769770.625, "dur": 36.852, + "args": { + "External id": 1414484,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769776.738, "dur": 2.483, + "args": { + "External id": 1414485,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769783.215, "dur": 0.316, + "args": { + "External id": 1414486,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769785.345, "dur": 0.606, + "args": { + "External id": 1414487,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769787.440, "dur": 0.611, + "args": { + "External id": 1414488,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769791.070, "dur": 0.568, + "args": { + "External id": 1414489,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769792.699, "dur": 0.638, + "args": { + "External id": 1414490,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769794.703, "dur": 3.710, + "args": { + "External id": 1414491,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769799.539, "dur": 0.528, + "args": { + "External id": 1414492,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769801.463, "dur": 0.265, + "args": { + "External id": 1414493,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533769820.251, "dur": 57.216, + "args": { + "External id": 1414494,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533769911.130, "dur": 124.159, + "args": { + "External id": 1414495,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533769922.692, "dur": 4.462, + "args": { + "External id": 1414496,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533769934.587, "dur": 10.598, + "args": { + "External id": 1414497,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533769939.000, "dur": 5.787, + "args": { + "External id": 1414498,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769942.941, "dur": 0.477, + "args": { + "External id": 1414499,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533769952.025, "dur": 28.766, + "args": { + "External id": 1414500,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769954.254, "dur": 2.090, + "args": { + "External id": 1414501,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769957.938, "dur": 0.457, + "args": { + "External id": 1414502,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769959.717, "dur": 0.498, + "args": { + "External id": 1414503,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769962.940, "dur": 2.318, + "args": { + "External id": 1414504,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769966.185, "dur": 0.385, + "args": { + "External id": 1414505,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769968.141, "dur": 0.406, + "args": { + "External id": 1414506,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769971.032, "dur": 0.380, + "args": { + "External id": 1414507,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769973.427, "dur": 0.241, + "args": { + "External id": 1414508,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533769974.836, "dur": 2.212, + "args": { + "External id": 1414509,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533769991.552, "dur": 35.973, + "args": { + "External id": 1414510,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533770132.841, "dur": 375.374, + "args": { + "External id": 1414511,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533770164.332, "dur": 338.154, + "args": { + "External id": 1414512,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17332, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533770174.722, "dur": 320.797, + "args": { + "External id": 1414513,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533770533.035, "dur": 2.116, + "args": { + "External id": 1414514,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17334, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338710, "tid": 2338710, + "ts": 6410533770631.897, "dur": 30498.801, + "args": { + "External id": 1414515,"Record function id": 0, "Ev Idx": 17335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770737.442, "dur": 7.063, + "args": { + "External id": 1414516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770748.103, "dur": 1.308, + "args": { + "External id": 1414517,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770751.196, "dur": 3.510, + "args": { + "External id": 1414518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770756.521, "dur": 1.308, + "args": { + "External id": 1414519,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770759.124, "dur": 1.063, + "args": { + "External id": 1414520,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770763.837, "dur": 0.839, + "args": { + "External id": 1414521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770766.498, "dur": 0.909, + "args": { + "External id": 1414522,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770768.975, "dur": 2.545, + "args": { + "External id": 1414523,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770772.754, "dur": 0.994, + "args": { + "External id": 1414524,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533770777.831, "dur": 0.711, + "args": { + "External id": 1414525,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533770795.829, "dur": 30248.494, + "args": { + "External id": 1414526,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533770811.343, "dur": 30220.148, + "args": { + "External id": 1414527,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533770828.336, "dur": 16.452, + "args": { + "External id": 1414528,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533770848.671, "dur": 30138.228, + "args": { + "External id": 1414529,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533770851.485, "dur": 30134.303, + "args": { + "External id": 1414530,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533770861.775, "dur": 15.859, + "args": { + "External id": 1414531,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533770879.711, "dur": 30101.089, + "args": { + "External id": 1414532,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533801293.681, "dur": 35.352, + "args": { + "External id": 1414533,"Sequence number": 15109092, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17353 + } + }, + { + "ph": "s", "id": 427, "pid": 2338710, "tid": 2338710, "ts": 6410533801293.681, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533801312.898, "dur": 11.523, + "args": { + "External id": 1414534,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533801318.013, "dur": 6.162, + "args": { + "External id": 1414535,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533801396.984, "dur": 83.208, + "args": { + "External id": 1414536,"Record function id": 0, "Ev Idx": 17356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533801482.954, "dur": 1148.484, + "args": { + "External id": 1414537,"Record function id": 0, "Ev Idx": 17357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533801522.630, "dur": 1095.499, + "args": { + "External id": 1414538,"Sequence number": 15109093, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17358 + } + }, + { + "ph": "s", "id": 426, "pid": 2338710, "tid": 2338710, "ts": 6410533801522.630, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533801590.962, "dur": 53.042, + "args": { + "External id": 1414539,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533801657.348, "dur": 105.536, + "args": { + "External id": 1414540,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533801774.917, "dur": 38.571, + "args": { + "External id": 1414541,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533801825.295, "dur": 30.275, + "args": { + "External id": 1414542,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533801883.171, "dur": 30.736, + "args": { + "External id": 1414543,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533801933.515, "dur": 18.467, + "args": { + "External id": 1414544,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533801975.034, "dur": 177.960, + "args": { + "External id": 1414545,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533802026.995, "dur": 11.691, + "args": { + "External id": 1414546,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533802032.552, "dur": 5.253, + "args": { + "External id": 1414547,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533802041.567, "dur": 4.428, + "args": { + "External id": 1414548,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533802047.474, "dur": 1.190, + "args": { + "External id": 1414549,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533802051.588, "dur": 42.369, + "args": { + "External id": 1414550,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533802166.047, "dur": 57.327, + "args": { + "External id": 1414551,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533802258.077, "dur": 32.465, + "args": { + "External id": 1414552,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533802300.830, "dur": 43.298, + "args": { + "External id": 1414553,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533802354.474, "dur": 35.120, + "args": { + "External id": 1414554,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533802427.315, "dur": 31.736, + "args": { + "External id": 1414555,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533802468.368, "dur": 42.319, + "args": { + "External id": 1414556,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533802530.391, "dur": 20.187, + "args": { + "External id": 1414557,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17377 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.10)", "pid": 2338710, "tid": 2338710, + "ts": 6410533802699.111, "dur": 79.974, + "args": { + "External id": 1414558,"Record function id": 0, "Ev Idx": 17378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533802854.622, "dur": 46.341, + "args": { + "External id": 1414559,"Record function id": 0, "Ev Idx": 17379 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 2338710, "tid": 2338710, + "ts": 6410533802910.458, "dur": 29931.050, + "args": { + "External id": 1414560,"Record function id": 0, "Ev Idx": 17380 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338710, "tid": 2338710, + "ts": 6410533802917.933, "dur": 958.429, + "args": { + "External id": 1414561,"Record function id": 0, "Ev Idx": 17381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533803004.916, "dur": 8.754, + "args": { + "External id": 1414562,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533803026.640, "dur": 76.838, + "args": { + "External id": 1414563,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803032.994, "dur": 2.498, + "args": { + "External id": 1414564,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803039.156, "dur": 0.374, + "args": { + "External id": 1414565,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803041.296, "dur": 0.423, + "args": { + "External id": 1414566,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803043.441, "dur": 0.488, + "args": { + "External id": 1414567,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803047.204, "dur": 0.765, + "args": { + "External id": 1414568,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803049.273, "dur": 0.459, + "args": { + "External id": 1414569,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803051.103, "dur": 40.287, + "args": { + "External id": 1414570,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803094.631, "dur": 0.532, + "args": { + "External id": 1414571,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803096.589, "dur": 0.440, + "args": { + "External id": 1414572,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533803116.176, "dur": 56.755, + "args": { + "External id": 1414573,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533803214.059, "dur": 126.883, + "args": { + "External id": 1414574,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533803227.052, "dur": 5.537, + "args": { + "External id": 1414575,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533803237.982, "dur": 11.189, + "args": { + "External id": 1414576,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533803243.117, "dur": 5.657, + "args": { + "External id": 1414577,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803246.843, "dur": 0.608, + "args": { + "External id": 1414578,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533803256.890, "dur": 31.292, + "args": { + "External id": 1414579,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803259.343, "dur": 1.577, + "args": { + "External id": 1414580,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803262.256, "dur": 0.932, + "args": { + "External id": 1414581,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803264.565, "dur": 0.575, + "args": { + "External id": 1414582,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803270.667, "dur": 2.391, + "args": { + "External id": 1414583,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803274.557, "dur": 0.366, + "args": { + "External id": 1414584,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803276.118, "dur": 0.515, + "args": { + "External id": 1414585,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803279.184, "dur": 0.486, + "args": { + "External id": 1414586,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803281.163, "dur": 0.437, + "args": { + "External id": 1414587,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533803282.983, "dur": 1.793, + "args": { + "External id": 1414588,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533803301.959, "dur": 31.091, + "args": { + "External id": 1414589,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533803397.256, "dur": 378.815, + "args": { + "External id": 1414590,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533803442.703, "dur": 328.161, + "args": { + "External id": 1414591,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17411, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533803454.455, "dur": 310.670, + "args": { + "External id": 1414592,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533803801.318, "dur": 2.269, + "args": { + "External id": 1414593,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17413, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338710, "tid": 2338710, + "ts": 6410533803896.350, "dur": 28723.494, + "args": { + "External id": 1414594,"Record function id": 0, "Ev Idx": 17414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804004.299, "dur": 6.813, + "args": { + "External id": 1414595,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804014.207, "dur": 0.945, + "args": { + "External id": 1414596,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804016.902, "dur": 3.434, + "args": { + "External id": 1414597,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804021.978, "dur": 0.907, + "args": { + "External id": 1414598,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804024.287, "dur": 0.938, + "args": { + "External id": 1414599,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804026.588, "dur": 1.008, + "args": { + "External id": 1414600,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804031.317, "dur": 1.046, + "args": { + "External id": 1414601,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804034.256, "dur": 2.036, + "args": { + "External id": 1414602,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804037.589, "dur": 0.895, + "args": { + "External id": 1414603,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533804040.072, "dur": 0.792, + "args": { + "External id": 1414604,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533804098.293, "dur": 28457.359, + "args": { + "External id": 1414605,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533804115.663, "dur": 28427.129, + "args": { + "External id": 1414606,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533804132.558, "dur": 16.805, + "args": { + "External id": 1414607,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533804153.143, "dur": 28345.268, + "args": { + "External id": 1414608,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533804155.720, "dur": 28341.644, + "args": { + "External id": 1414609,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533804161.388, "dur": 6.825, + "args": { + "External id": 1414610,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533804169.952, "dur": 28322.774, + "args": { + "External id": 1414611,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533832780.277, "dur": 34.310, + "args": { + "External id": 1414612,"Sequence number": 15109094, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17432 + } + }, + { + "ph": "s", "id": 425, "pid": 2338710, "tid": 2338710, "ts": 6410533832780.277, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533832798.568, "dur": 11.226, + "args": { + "External id": 1414613,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533832803.338, "dur": 6.216, + "args": { + "External id": 1414614,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533832883.063, "dur": 71.361, + "args": { + "External id": 1414615,"Record function id": 0, "Ev Idx": 17435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533832955.941, "dur": 1170.089, + "args": { + "External id": 1414616,"Record function id": 0, "Ev Idx": 17436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533832996.475, "dur": 1114.094, + "args": { + "External id": 1414617,"Sequence number": 15109095, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17437 + } + }, + { + "ph": "s", "id": 424, "pid": 2338710, "tid": 2338710, "ts": 6410533832996.475, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533833097.035, "dur": 54.221, + "args": { + "External id": 1414618,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533833166.564, "dur": 105.716, + "args": { + "External id": 1414619,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533833283.992, "dur": 41.643, + "args": { + "External id": 1414620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533833337.721, "dur": 30.184, + "args": { + "External id": 1414621,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533833398.910, "dur": 42.512, + "args": { + "External id": 1414622,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533833463.456, "dur": 20.932, + "args": { + "External id": 1414623,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533833507.959, "dur": 138.705, + "args": { + "External id": 1414624,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533833560.306, "dur": 12.089, + "args": { + "External id": 1414625,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533833565.888, "dur": 5.652, + "args": { + "External id": 1414626,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533833575.181, "dur": 4.004, + "args": { + "External id": 1414627,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533833581.080, "dur": 1.258, + "args": { + "External id": 1414628,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533833584.965, "dur": 7.864, + "args": { + "External id": 1414629,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533833657.323, "dur": 54.065, + "args": { + "External id": 1414630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533833744.430, "dur": 32.740, + "args": { + "External id": 1414631,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533833786.979, "dur": 43.503, + "args": { + "External id": 1414632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533833839.249, "dur": 35.388, + "args": { + "External id": 1414633,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533833896.966, "dur": 28.924, + "args": { + "External id": 1414634,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533833935.426, "dur": 36.534, + "args": { + "External id": 1414635,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533833991.843, "dur": 20.447, + "args": { + "External id": 1414636,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17456 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.11)", "pid": 2338710, "tid": 2338710, + "ts": 6410533834195.391, "dur": 81.174, + "args": { + "External id": 1414637,"Record function id": 0, "Ev Idx": 17457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533834353.428, "dur": 46.314, + "args": { + "External id": 1414638,"Record function id": 0, "Ev Idx": 17458 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 2338710, "tid": 2338710, + "ts": 6410533834408.453, "dur": 31317.674, + "args": { + "External id": 1414639,"Record function id": 0, "Ev Idx": 17459 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338710, "tid": 2338710, + "ts": 6410533834434.143, "dur": 958.082, + "args": { + "External id": 1414640,"Record function id": 0, "Ev Idx": 17460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533834519.702, "dur": 9.983, + "args": { + "External id": 1414641,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533834543.488, "dur": 37.423, + "args": { + "External id": 1414642,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834549.954, "dur": 2.419, + "args": { + "External id": 1414643,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834556.242, "dur": 0.402, + "args": { + "External id": 1414644,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834558.213, "dur": 0.588, + "args": { + "External id": 1414645,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834560.299, "dur": 0.639, + "args": { + "External id": 1414646,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834563.694, "dur": 0.744, + "args": { + "External id": 1414647,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834565.573, "dur": 0.523, + "args": { + "External id": 1414648,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834567.649, "dur": 4.042, + "args": { + "External id": 1414649,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834572.884, "dur": 0.560, + "args": { + "External id": 1414650,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834574.579, "dur": 0.626, + "args": { + "External id": 1414651,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533834592.795, "dur": 55.157, + "args": { + "External id": 1414652,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533834681.445, "dur": 147.357, + "args": { + "External id": 1414653,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533834692.319, "dur": 4.156, + "args": { + "External id": 1414654,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533834701.725, "dur": 35.370, + "args": { + "External id": 1414655,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533834706.306, "dur": 30.365, + "args": { + "External id": 1414656,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834734.507, "dur": 0.562, + "args": { + "External id": 1414657,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533834750.943, "dur": 24.743, + "args": { + "External id": 1414658,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834752.616, "dur": 1.504, + "args": { + "External id": 1414659,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834755.531, "dur": 0.263, + "args": { + "External id": 1414660,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834756.883, "dur": 0.288, + "args": { + "External id": 1414661,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834759.899, "dur": 1.951, + "args": { + "External id": 1414662,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834763.132, "dur": 0.308, + "args": { + "External id": 1414663,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834764.464, "dur": 0.307, + "args": { + "External id": 1414664,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834766.897, "dur": 0.275, + "args": { + "External id": 1414665,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834768.392, "dur": 0.320, + "args": { + "External id": 1414666,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533834770.118, "dur": 1.343, + "args": { + "External id": 1414667,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533834786.868, "dur": 33.437, + "args": { + "External id": 1414668,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533834881.623, "dur": 402.707, + "args": { + "External id": 1414669,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533834912.187, "dur": 366.356, + "args": { + "External id": 1414670,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17490, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533834922.568, "dur": 349.940, + "args": { + "External id": 1414671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533835313.724, "dur": 2.458, + "args": { + "External id": 1414672,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17492, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338710, "tid": 2338710, + "ts": 6410533835412.992, "dur": 30088.075, + "args": { + "External id": 1414673,"Record function id": 0, "Ev Idx": 17493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835535.217, "dur": 7.036, + "args": { + "External id": 1414674,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835545.455, "dur": 0.879, + "args": { + "External id": 1414675,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835547.848, "dur": 3.459, + "args": { + "External id": 1414676,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835552.941, "dur": 0.862, + "args": { + "External id": 1414677,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835555.193, "dur": 1.013, + "args": { + "External id": 1414678,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835557.293, "dur": 0.733, + "args": { + "External id": 1414679,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835559.494, "dur": 0.746, + "args": { + "External id": 1414680,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835561.862, "dur": 2.025, + "args": { + "External id": 1414681,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835567.216, "dur": 0.784, + "args": { + "External id": 1414682,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533835569.420, "dur": 1.118, + "args": { + "External id": 1414683,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533835588.431, "dur": 29850.780, + "args": { + "External id": 1414684,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533835603.606, "dur": 29823.423, + "args": { + "External id": 1414685,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533835619.727, "dur": 17.542, + "args": { + "External id": 1414686,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533835640.715, "dur": 29731.670, + "args": { + "External id": 1414687,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533835643.277, "dur": 29727.965, + "args": { + "External id": 1414688,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533835648.549, "dur": 6.618, + "args": { + "External id": 1414689,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533835659.203, "dur": 29706.815, + "args": { + "External id": 1414690,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533865663.087, "dur": 36.625, + "args": { + "External id": 1414691,"Sequence number": 15109096, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17511 + } + }, + { + "ph": "s", "id": 423, "pid": 2338710, "tid": 2338710, "ts": 6410533865663.087, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533865683.232, "dur": 11.720, + "args": { + "External id": 1414692,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533865688.237, "dur": 6.482, + "args": { + "External id": 1414693,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533865767.410, "dur": 71.104, + "args": { + "External id": 1414694,"Record function id": 0, "Ev Idx": 17514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533865839.899, "dur": 1117.157, + "args": { + "External id": 1414695,"Record function id": 0, "Ev Idx": 17515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533865876.940, "dur": 1065.644, + "args": { + "External id": 1414696,"Sequence number": 15109097, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17516 + } + }, + { + "ph": "s", "id": 422, "pid": 2338710, "tid": 2338710, "ts": 6410533865876.940, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533865945.255, "dur": 53.208, + "args": { + "External id": 1414697,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533866010.960, "dur": 134.457, + "args": { + "External id": 1414698,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533866160.775, "dur": 41.541, + "args": { + "External id": 1414699,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533866211.441, "dur": 30.324, + "args": { + "External id": 1414700,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533866270.867, "dur": 26.714, + "args": { + "External id": 1414701,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533866319.508, "dur": 17.701, + "args": { + "External id": 1414702,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533866360.041, "dur": 150.908, + "args": { + "External id": 1414703,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533866409.997, "dur": 29.022, + "args": { + "External id": 1414704,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533866430.951, "dur": 7.103, + "args": { + "External id": 1414705,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533866442.030, "dur": 3.917, + "args": { + "External id": 1414706,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533866447.189, "dur": 0.940, + "args": { + "External id": 1414707,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533866450.861, "dur": 5.987, + "args": { + "External id": 1414708,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533866522.436, "dur": 53.498, + "args": { + "External id": 1414709,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533866609.003, "dur": 29.260, + "args": { + "External id": 1414710,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533866648.896, "dur": 43.091, + "args": { + "External id": 1414711,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533866701.980, "dur": 35.945, + "args": { + "External id": 1414712,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533866761.514, "dur": 29.782, + "args": { + "External id": 1414713,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533866799.165, "dur": 37.275, + "args": { + "External id": 1414714,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533866857.075, "dur": 20.080, + "args": { + "External id": 1414715,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.12)", "pid": 2338710, "tid": 2338710, + "ts": 6410533867022.416, "dur": 123.084, + "args": { + "External id": 1414716,"Record function id": 0, "Ev Idx": 17536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533867224.570, "dur": 48.978, + "args": { + "External id": 1414717,"Record function id": 0, "Ev Idx": 17537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 2338710, "tid": 2338710, + "ts": 6410533867282.780, "dur": 30652.606, + "args": { + "External id": 1414718,"Record function id": 0, "Ev Idx": 17538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338710, "tid": 2338710, + "ts": 6410533867291.012, "dur": 954.809, + "args": { + "External id": 1414719,"Record function id": 0, "Ev Idx": 17539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533867379.698, "dur": 9.970, + "args": { + "External id": 1414720,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533867402.926, "dur": 54.423, + "args": { + "External id": 1414721,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867409.072, "dur": 2.478, + "args": { + "External id": 1414722,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867429.055, "dur": 0.835, + "args": { + "External id": 1414723,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867432.644, "dur": 0.432, + "args": { + "External id": 1414724,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867434.662, "dur": 0.854, + "args": { + "External id": 1414725,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867438.808, "dur": 0.436, + "args": { + "External id": 1414726,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867440.560, "dur": 0.589, + "args": { + "External id": 1414727,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867443.065, "dur": 3.681, + "args": { + "External id": 1414728,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867448.105, "dur": 0.524, + "args": { + "External id": 1414729,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867450.123, "dur": 0.694, + "args": { + "External id": 1414730,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533867469.593, "dur": 58.357, + "args": { + "External id": 1414731,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533867572.623, "dur": 120.786, + "args": { + "External id": 1414732,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533867584.942, "dur": 5.639, + "args": { + "External id": 1414733,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533867595.719, "dur": 10.710, + "args": { + "External id": 1414734,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533867600.295, "dur": 5.740, + "args": { + "External id": 1414735,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867604.302, "dur": 0.472, + "args": { + "External id": 1414736,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533867613.102, "dur": 27.108, + "args": { + "External id": 1414737,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867615.885, "dur": 0.360, + "args": { + "External id": 1414738,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867618.138, "dur": 1.852, + "args": { + "External id": 1414739,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867620.895, "dur": 0.726, + "args": { + "External id": 1414740,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867623.079, "dur": 2.366, + "args": { + "External id": 1414741,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867627.805, "dur": 0.325, + "args": { + "External id": 1414742,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867629.610, "dur": 0.292, + "args": { + "External id": 1414743,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867631.045, "dur": 0.311, + "args": { + "External id": 1414744,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867633.783, "dur": 0.233, + "args": { + "External id": 1414745,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533867635.762, "dur": 0.285, + "args": { + "External id": 1414746,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533867652.880, "dur": 32.468, + "args": { + "External id": 1414747,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533867748.081, "dur": 393.103, + "args": { + "External id": 1414748,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533867779.521, "dur": 355.529, + "args": { + "External id": 1414749,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17569, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533867789.743, "dur": 339.207, + "args": { + "External id": 1414750,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533868169.110, "dur": 2.745, + "args": { + "External id": 1414751,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17571, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338710, "tid": 2338710, + "ts": 6410533868266.177, "dur": 29440.141, + "args": { + "External id": 1414752,"Record function id": 0, "Ev Idx": 17572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868370.497, "dur": 6.490, + "args": { + "External id": 1414753,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868380.731, "dur": 0.853, + "args": { + "External id": 1414754,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868383.172, "dur": 3.953, + "args": { + "External id": 1414755,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868388.630, "dur": 0.926, + "args": { + "External id": 1414756,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868390.905, "dur": 1.025, + "args": { + "External id": 1414757,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868393.089, "dur": 0.824, + "args": { + "External id": 1414758,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868395.957, "dur": 0.714, + "args": { + "External id": 1414759,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868398.269, "dur": 2.411, + "args": { + "External id": 1414760,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868402.297, "dur": 1.002, + "args": { + "External id": 1414761,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533868406.604, "dur": 1.227, + "args": { + "External id": 1414762,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533868441.527, "dur": 29200.501, + "args": { + "External id": 1414763,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533868457.473, "dur": 29172.387, + "args": { + "External id": 1414764,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533868473.877, "dur": 17.224, + "args": { + "External id": 1414765,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533868494.788, "dur": 29089.926, + "args": { + "External id": 1414766,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533868497.655, "dur": 29085.927, + "args": { + "External id": 1414767,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533868503.364, "dur": 6.711, + "args": { + "External id": 1414768,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533868512.291, "dur": 29066.268, + "args": { + "External id": 1414769,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533897869.208, "dur": 36.563, + "args": { + "External id": 1414770,"Sequence number": 15109098, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17590 + } + }, + { + "ph": "s", "id": 421, "pid": 2338710, "tid": 2338710, "ts": 6410533897869.208, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533897889.591, "dur": 11.566, + "args": { + "External id": 1414771,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533897894.735, "dur": 6.207, + "args": { + "External id": 1414772,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533897977.424, "dur": 71.355, + "args": { + "External id": 1414773,"Record function id": 0, "Ev Idx": 17593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533898050.355, "dur": 1171.143, + "args": { + "External id": 1414774,"Record function id": 0, "Ev Idx": 17594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533898129.275, "dur": 1077.968, + "args": { + "External id": 1414775,"Sequence number": 15109099, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17595 + } + }, + { + "ph": "s", "id": 420, "pid": 2338710, "tid": 2338710, "ts": 6410533898129.275, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533898200.348, "dur": 54.401, + "args": { + "External id": 1414776,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533898267.214, "dur": 102.813, + "args": { + "External id": 1414777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533898382.507, "dur": 53.682, + "args": { + "External id": 1414778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533898445.849, "dur": 34.718, + "args": { + "External id": 1414779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533898510.828, "dur": 29.102, + "args": { + "External id": 1414780,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533898561.449, "dur": 18.581, + "args": { + "External id": 1414781,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533898603.017, "dur": 132.806, + "args": { + "External id": 1414782,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533898654.223, "dur": 11.035, + "args": { + "External id": 1414783,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533898659.264, "dur": 5.263, + "args": { + "External id": 1414784,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533898668.036, "dur": 4.232, + "args": { + "External id": 1414785,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533898673.622, "dur": 0.847, + "args": { + "External id": 1414786,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533898678.930, "dur": 5.995, + "args": { + "External id": 1414787,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533898745.936, "dur": 49.641, + "args": { + "External id": 1414788,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533898827.826, "dur": 32.347, + "args": { + "External id": 1414789,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533898870.858, "dur": 43.340, + "args": { + "External id": 1414790,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533898922.774, "dur": 35.142, + "args": { + "External id": 1414791,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533898982.397, "dur": 31.341, + "args": { + "External id": 1414792,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533899019.705, "dur": 69.988, + "args": { + "External id": 1414793,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533899113.273, "dur": 21.331, + "args": { + "External id": 1414794,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17614 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.13)", "pid": 2338710, "tid": 2338710, + "ts": 6410533899286.371, "dur": 79.276, + "args": { + "External id": 1414795,"Record function id": 0, "Ev Idx": 17615 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533899463.005, "dur": 48.766, + "args": { + "External id": 1414796,"Record function id": 0, "Ev Idx": 17616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 2338710, "tid": 2338710, + "ts": 6410533899521.116, "dur": 30133.384, + "args": { + "External id": 1414797,"Record function id": 0, "Ev Idx": 17617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338710, "tid": 2338710, + "ts": 6410533899531.357, "dur": 816.485, + "args": { + "External id": 1414798,"Record function id": 0, "Ev Idx": 17618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533899616.945, "dur": 9.892, + "args": { + "External id": 1414799,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533899640.445, "dur": 41.398, + "args": { + "External id": 1414800,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899646.814, "dur": 2.304, + "args": { + "External id": 1414801,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899653.227, "dur": 0.412, + "args": { + "External id": 1414802,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899657.834, "dur": 0.393, + "args": { + "External id": 1414803,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899659.553, "dur": 0.346, + "args": { + "External id": 1414804,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899663.816, "dur": 0.582, + "args": { + "External id": 1414805,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899665.459, "dur": 0.498, + "args": { + "External id": 1414806,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899667.429, "dur": 4.651, + "args": { + "External id": 1414807,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899673.129, "dur": 0.460, + "args": { + "External id": 1414808,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899675.032, "dur": 0.484, + "args": { + "External id": 1414809,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533899693.217, "dur": 56.528, + "args": { + "External id": 1414810,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533899784.462, "dur": 122.423, + "args": { + "External id": 1414811,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533899795.925, "dur": 4.418, + "args": { + "External id": 1414812,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533899806.285, "dur": 11.254, + "args": { + "External id": 1414813,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533899810.964, "dur": 6.121, + "args": { + "External id": 1414814,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899814.973, "dur": 0.857, + "args": { + "External id": 1414815,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533899824.429, "dur": 30.810, + "args": { + "External id": 1414816,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899826.129, "dur": 2.716, + "args": { + "External id": 1414817,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899830.325, "dur": 0.446, + "args": { + "External id": 1414818,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899832.093, "dur": 0.764, + "args": { + "External id": 1414819,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899836.168, "dur": 2.267, + "args": { + "External id": 1414820,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899839.733, "dur": 0.476, + "args": { + "External id": 1414821,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899841.719, "dur": 0.586, + "args": { + "External id": 1414822,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899845.253, "dur": 0.274, + "args": { + "External id": 1414823,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899847.009, "dur": 0.542, + "args": { + "External id": 1414824,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533899848.765, "dur": 1.593, + "args": { + "External id": 1414825,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533899865.991, "dur": 33.374, + "args": { + "External id": 1414826,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533899958.402, "dur": 292.520, + "args": { + "External id": 1414827,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533899989.394, "dur": 256.213, + "args": { + "External id": 1414828,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17648, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533899999.406, "dur": 240.125, + "args": { + "External id": 1414829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533900276.895, "dur": 2.195, + "args": { + "External id": 1414830,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17650, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338710, "tid": 2338710, + "ts": 6410533900367.692, "dur": 29060.706, + "args": { + "External id": 1414831,"Record function id": 0, "Ev Idx": 17651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900484.446, "dur": 6.621, + "args": { + "External id": 1414832,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900494.953, "dur": 1.216, + "args": { + "External id": 1414833,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900497.927, "dur": 3.606, + "args": { + "External id": 1414834,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900503.223, "dur": 0.846, + "args": { + "External id": 1414835,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900505.354, "dur": 1.109, + "args": { + "External id": 1414836,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900507.893, "dur": 1.127, + "args": { + "External id": 1414837,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900510.533, "dur": 0.730, + "args": { + "External id": 1414838,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900513.236, "dur": 2.212, + "args": { + "External id": 1414839,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900517.135, "dur": 0.728, + "args": { + "External id": 1414840,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533900521.220, "dur": 1.161, + "args": { + "External id": 1414841,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533900540.629, "dur": 28819.847, + "args": { + "External id": 1414842,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533900556.200, "dur": 28792.361, + "args": { + "External id": 1414843,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533900571.842, "dur": 15.952, + "args": { + "External id": 1414844,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533900591.354, "dur": 28714.966, + "args": { + "External id": 1414845,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533900593.946, "dur": 28711.221, + "args": { + "External id": 1414846,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533900600.057, "dur": 5.880, + "args": { + "External id": 1414847,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533900607.699, "dur": 28693.277, + "args": { + "External id": 1414848,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533929589.063, "dur": 35.080, + "args": { + "External id": 1414849,"Sequence number": 15109100, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17669 + } + }, + { + "ph": "s", "id": 419, "pid": 2338710, "tid": 2338710, "ts": 6410533929589.063, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533929607.894, "dur": 11.599, + "args": { + "External id": 1414850,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533929612.665, "dur": 6.557, + "args": { + "External id": 1414851,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533929696.070, "dur": 71.860, + "args": { + "External id": 1414852,"Record function id": 0, "Ev Idx": 17672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533929769.455, "dur": 1131.943, + "args": { + "External id": 1414853,"Record function id": 0, "Ev Idx": 17673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533929807.206, "dur": 1080.440, + "args": { + "External id": 1414854,"Sequence number": 15109101, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17674 + } + }, + { + "ph": "s", "id": 418, "pid": 2338710, "tid": 2338710, "ts": 6410533929807.206, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533929873.414, "dur": 51.604, + "args": { + "External id": 1414855,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533929937.608, "dur": 105.287, + "args": { + "External id": 1414856,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533930092.426, "dur": 45.353, + "args": { + "External id": 1414857,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533930149.651, "dur": 31.141, + "args": { + "External id": 1414858,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533930211.158, "dur": 31.252, + "args": { + "External id": 1414859,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533930266.265, "dur": 17.564, + "args": { + "External id": 1414860,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533930306.826, "dur": 145.466, + "args": { + "External id": 1414861,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533930356.064, "dur": 12.084, + "args": { + "External id": 1414862,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533930361.995, "dur": 5.268, + "args": { + "External id": 1414863,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533930370.873, "dur": 4.819, + "args": { + "External id": 1414864,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533930377.322, "dur": 1.055, + "args": { + "External id": 1414865,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533930380.742, "dur": 5.049, + "args": { + "External id": 1414866,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533930465.139, "dur": 56.264, + "args": { + "External id": 1414867,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533930554.725, "dur": 30.547, + "args": { + "External id": 1414868,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533930595.408, "dur": 46.300, + "args": { + "External id": 1414869,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533930652.278, "dur": 35.775, + "args": { + "External id": 1414870,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533930712.374, "dur": 25.892, + "args": { + "External id": 1414871,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533930746.904, "dur": 36.564, + "args": { + "External id": 1414872,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533930801.313, "dur": 18.195, + "args": { + "External id": 1414873,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17693 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.14)", "pid": 2338710, "tid": 2338710, + "ts": 6410533930969.287, "dur": 80.705, + "args": { + "External id": 1414874,"Record function id": 0, "Ev Idx": 17694 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533931172.611, "dur": 50.812, + "args": { + "External id": 1414875,"Record function id": 0, "Ev Idx": 17695 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 2338710, "tid": 2338710, + "ts": 6410533931233.701, "dur": 32352.694, + "args": { + "External id": 1414876,"Record function id": 0, "Ev Idx": 17696 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338710, "tid": 2338710, + "ts": 6410533931241.367, "dur": 1004.937, + "args": { + "External id": 1414877,"Record function id": 0, "Ev Idx": 17697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533931328.880, "dur": 9.674, + "args": { + "External id": 1414878,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533931351.758, "dur": 38.938, + "args": { + "External id": 1414879,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931357.722, "dur": 2.228, + "args": { + "External id": 1414880,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931364.375, "dur": 0.612, + "args": { + "External id": 1414881,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931367.083, "dur": 0.712, + "args": { + "External id": 1414882,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931369.344, "dur": 0.416, + "args": { + "External id": 1414883,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931373.527, "dur": 0.493, + "args": { + "External id": 1414884,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931375.135, "dur": 0.435, + "args": { + "External id": 1414885,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931376.760, "dur": 4.387, + "args": { + "External id": 1414886,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931382.415, "dur": 0.283, + "args": { + "External id": 1414887,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931383.910, "dur": 0.268, + "args": { + "External id": 1414888,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533931403.597, "dur": 73.171, + "args": { + "External id": 1414889,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533931514.500, "dur": 132.215, + "args": { + "External id": 1414890,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533931526.886, "dur": 5.209, + "args": { + "External id": 1414891,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533931537.545, "dur": 11.162, + "args": { + "External id": 1414892,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533931542.441, "dur": 5.886, + "args": { + "External id": 1414893,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931546.032, "dur": 0.699, + "args": { + "External id": 1414894,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533931555.408, "dur": 34.000, + "args": { + "External id": 1414895,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931557.697, "dur": 2.377, + "args": { + "External id": 1414896,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931561.968, "dur": 0.365, + "args": { + "External id": 1414897,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931563.871, "dur": 0.550, + "args": { + "External id": 1414898,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931567.967, "dur": 2.744, + "args": { + "External id": 1414899,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931572.004, "dur": 0.517, + "args": { + "External id": 1414900,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931574.000, "dur": 0.577, + "args": { + "External id": 1414901,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931578.049, "dur": 0.446, + "args": { + "External id": 1414902,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931580.118, "dur": 0.448, + "args": { + "External id": 1414903,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533931582.047, "dur": 2.240, + "args": { + "External id": 1414904,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533931603.186, "dur": 35.218, + "args": { + "External id": 1414905,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533931703.636, "dur": 433.452, + "args": { + "External id": 1414906,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533931735.516, "dur": 395.705, + "args": { + "External id": 1414907,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17727, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533931745.569, "dur": 379.032, + "args": { + "External id": 1414908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533932166.837, "dur": 2.514, + "args": { + "External id": 1414909,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17729, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338710, "tid": 2338710, + "ts": 6410533932266.881, "dur": 31072.120, + "args": { + "External id": 1414910,"Record function id": 0, "Ev Idx": 17730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932374.479, "dur": 6.742, + "args": { + "External id": 1414911,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932385.151, "dur": 0.880, + "args": { + "External id": 1414912,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932387.614, "dur": 3.382, + "args": { + "External id": 1414913,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932392.862, "dur": 0.878, + "args": { + "External id": 1414914,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932395.202, "dur": 1.098, + "args": { + "External id": 1414915,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932397.584, "dur": 0.952, + "args": { + "External id": 1414916,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932400.261, "dur": 0.851, + "args": { + "External id": 1414917,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932403.161, "dur": 2.206, + "args": { + "External id": 1414918,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932406.798, "dur": 0.937, + "args": { + "External id": 1414919,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533932409.284, "dur": 0.560, + "args": { + "External id": 1414920,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533932447.059, "dur": 30825.714, + "args": { + "External id": 1414921,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533932464.258, "dur": 30796.041, + "args": { + "External id": 1414922,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533932479.714, "dur": 18.126, + "args": { + "External id": 1414923,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533932501.705, "dur": 30713.968, + "args": { + "External id": 1414924,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533932504.507, "dur": 30709.930, + "args": { + "External id": 1414925,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533932510.604, "dur": 5.799, + "args": { + "External id": 1414926,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533932518.236, "dur": 30691.479, + "args": { + "External id": 1414927,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533963519.463, "dur": 38.338, + "args": { + "External id": 1414928,"Sequence number": 15109102, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17748 + } + }, + { + "ph": "s", "id": 417, "pid": 2338710, "tid": 2338710, "ts": 6410533963519.463, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533963540.523, "dur": 12.318, + "args": { + "External id": 1414929,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533963545.722, "dur": 6.595, + "args": { + "External id": 1414930,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533963627.868, "dur": 74.284, + "args": { + "External id": 1414931,"Record function id": 0, "Ev Idx": 17751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533963703.487, "dur": 1134.072, + "args": { + "External id": 1414932,"Record function id": 0, "Ev Idx": 17752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533963743.817, "dur": 1080.041, + "args": { + "External id": 1414933,"Sequence number": 15109103, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17753 + } + }, + { + "ph": "s", "id": 416, "pid": 2338710, "tid": 2338710, "ts": 6410533963743.817, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533963810.109, "dur": 51.973, + "args": { + "External id": 1414934,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533963874.893, "dur": 103.637, + "args": { + "External id": 1414935,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533963993.321, "dur": 41.330, + "args": { + "External id": 1414936,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533964041.558, "dur": 68.066, + "args": { + "External id": 1414937,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533964144.464, "dur": 31.480, + "args": { + "External id": 1414938,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533964196.727, "dur": 19.363, + "args": { + "External id": 1414939,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533964240.847, "dur": 134.708, + "args": { + "External id": 1414940,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533964293.636, "dur": 12.603, + "args": { + "External id": 1414941,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533964299.095, "dur": 6.093, + "args": { + "External id": 1414942,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533964308.923, "dur": 4.432, + "args": { + "External id": 1414943,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533964314.797, "dur": 1.190, + "args": { + "External id": 1414944,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533964320.566, "dur": 5.384, + "args": { + "External id": 1414945,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533964386.235, "dur": 69.348, + "args": { + "External id": 1414946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533964492.516, "dur": 31.107, + "args": { + "External id": 1414947,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533964534.208, "dur": 46.237, + "args": { + "External id": 1414948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533964589.625, "dur": 35.420, + "args": { + "External id": 1414949,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533964648.844, "dur": 29.996, + "args": { + "External id": 1414950,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533964684.724, "dur": 36.237, + "args": { + "External id": 1414951,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533964739.035, "dur": 17.220, + "args": { + "External id": 1414952,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.15)", "pid": 2338710, "tid": 2338710, + "ts": 6410533964904.293, "dur": 83.856, + "args": { + "External id": 1414953,"Record function id": 0, "Ev Idx": 17773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533965103.575, "dur": 51.382, + "args": { + "External id": 1414954,"Record function id": 0, "Ev Idx": 17774 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 2338710, "tid": 2338710, + "ts": 6410533965164.946, "dur": 30592.101, + "args": { + "External id": 1414955,"Record function id": 0, "Ev Idx": 17775 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338710, "tid": 2338710, + "ts": 6410533965174.328, "dur": 962.107, + "args": { + "External id": 1414956,"Record function id": 0, "Ev Idx": 17776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533965263.142, "dur": 9.957, + "args": { + "External id": 1414957,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533965287.356, "dur": 54.131, + "args": { + "External id": 1414958,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965293.637, "dur": 2.110, + "args": { + "External id": 1414959,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965300.570, "dur": 0.377, + "args": { + "External id": 1414960,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965302.454, "dur": 0.549, + "args": { + "External id": 1414961,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965304.126, "dur": 0.695, + "args": { + "External id": 1414962,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965307.705, "dur": 0.622, + "args": { + "External id": 1414963,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965313.505, "dur": 0.632, + "args": { + "External id": 1414964,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965324.611, "dur": 4.810, + "args": { + "External id": 1414965,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965330.580, "dur": 0.359, + "args": { + "External id": 1414966,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965334.793, "dur": 0.367, + "args": { + "External id": 1414967,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533965353.632, "dur": 59.105, + "args": { + "External id": 1414968,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533965464.157, "dur": 129.725, + "args": { + "External id": 1414969,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533965475.793, "dur": 5.903, + "args": { + "External id": 1414970,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533965487.333, "dur": 12.719, + "args": { + "External id": 1414971,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533965491.984, "dur": 7.646, + "args": { + "External id": 1414972,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965495.542, "dur": 2.178, + "args": { + "External id": 1414973,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533965506.875, "dur": 30.204, + "args": { + "External id": 1414974,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965508.973, "dur": 0.567, + "args": { + "External id": 1414975,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965511.477, "dur": 0.887, + "args": { + "External id": 1414976,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965513.811, "dur": 0.456, + "args": { + "External id": 1414977,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965517.154, "dur": 3.076, + "args": { + "External id": 1414978,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965521.277, "dur": 0.296, + "args": { + "External id": 1414979,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965523.203, "dur": 1.664, + "args": { + "External id": 1414980,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965525.793, "dur": 0.496, + "args": { + "External id": 1414981,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965527.546, "dur": 0.404, + "args": { + "External id": 1414982,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533965531.667, "dur": 0.263, + "args": { + "External id": 1414983,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533965548.442, "dur": 37.268, + "args": { + "External id": 1414984,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533965648.770, "dur": 354.987, + "args": { + "External id": 1414985,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533965679.631, "dur": 319.017, + "args": { + "External id": 1414986,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17806, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533965690.012, "dur": 303.348, + "args": { + "External id": 1414987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533966028.527, "dur": 2.030, + "args": { + "External id": 1414988,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17808, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338710, "tid": 2338710, + "ts": 6410533966159.386, "dur": 29380.433, + "args": { + "External id": 1414989,"Record function id": 0, "Ev Idx": 17809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966265.995, "dur": 6.990, + "args": { + "External id": 1414990,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966276.095, "dur": 1.065, + "args": { + "External id": 1414991,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966279.087, "dur": 3.355, + "args": { + "External id": 1414992,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966284.169, "dur": 1.161, + "args": { + "External id": 1414993,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966286.815, "dur": 1.060, + "args": { + "External id": 1414994,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966289.048, "dur": 0.714, + "args": { + "External id": 1414995,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966291.212, "dur": 0.812, + "args": { + "External id": 1414996,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966293.966, "dur": 2.556, + "args": { + "External id": 1414997,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966297.849, "dur": 0.944, + "args": { + "External id": 1414998,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533966302.510, "dur": 0.792, + "args": { + "External id": 1414999,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533966320.954, "dur": 29160.149, + "args": { + "External id": 1415000,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533966337.090, "dur": 29132.852, + "args": { + "External id": 1415001,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533966353.239, "dur": 17.153, + "args": { + "External id": 1415002,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533966374.122, "dur": 29051.975, + "args": { + "External id": 1415003,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533966376.512, "dur": 29048.204, + "args": { + "External id": 1415004,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533966382.442, "dur": 6.344, + "args": { + "External id": 1415005,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533966390.679, "dur": 29019.554, + "args": { + "External id": 1415006,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533995696.210, "dur": 34.353, + "args": { + "External id": 1415007,"Sequence number": 15109104, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17827 + } + }, + { + "ph": "s", "id": 415, "pid": 2338710, "tid": 2338710, "ts": 6410533995696.210, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410533995714.818, "dur": 10.908, + "args": { + "External id": 1415008,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533995719.556, "dur": 5.905, + "args": { + "External id": 1415009,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410533995796.666, "dur": 69.967, + "args": { + "External id": 1415010,"Record function id": 0, "Ev Idx": 17830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410533995867.861, "dur": 1114.943, + "args": { + "External id": 1415011,"Record function id": 0, "Ev Idx": 17831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410533995905.327, "dur": 1063.655, + "args": { + "External id": 1415012,"Sequence number": 15109105, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17832 + } + }, + { + "ph": "s", "id": 414, "pid": 2338710, "tid": 2338710, "ts": 6410533995905.327, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533995971.698, "dur": 48.295, + "args": { + "External id": 1415013,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533996032.612, "dur": 133.888, + "args": { + "External id": 1415014,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533996183.667, "dur": 42.549, + "args": { + "External id": 1415015,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533996235.489, "dur": 29.931, + "args": { + "External id": 1415016,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533996294.029, "dur": 27.584, + "args": { + "External id": 1415017,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410533996344.889, "dur": 16.585, + "args": { + "External id": 1415018,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410533996384.864, "dur": 152.224, + "args": { + "External id": 1415019,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410533996454.120, "dur": 12.936, + "args": { + "External id": 1415020,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533996459.761, "dur": 6.140, + "args": { + "External id": 1415021,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533996469.773, "dur": 4.401, + "args": { + "External id": 1415022,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533996475.321, "dur": 1.065, + "args": { + "External id": 1415023,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533996478.983, "dur": 5.079, + "args": { + "External id": 1415024,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533996548.781, "dur": 52.917, + "args": { + "External id": 1415025,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410533996635.161, "dur": 30.591, + "args": { + "External id": 1415026,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533996675.768, "dur": 43.351, + "args": { + "External id": 1415027,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533996730.598, "dur": 35.167, + "args": { + "External id": 1415028,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410533996790.218, "dur": 25.731, + "args": { + "External id": 1415029,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410533996823.845, "dur": 38.159, + "args": { + "External id": 1415030,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410533996880.451, "dur": 20.432, + "args": { + "External id": 1415031,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17851 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.16)", "pid": 2338710, "tid": 2338710, + "ts": 6410533997048.277, "dur": 137.426, + "args": { + "External id": 1415032,"Record function id": 0, "Ev Idx": 17852 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410533997267.872, "dur": 51.169, + "args": { + "External id": 1415033,"Record function id": 0, "Ev Idx": 17853 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 2338710, "tid": 2338710, + "ts": 6410533997327.515, "dur": 31319.429, + "args": { + "External id": 1415034,"Record function id": 0, "Ev Idx": 17854 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338710, "tid": 2338710, + "ts": 6410533997336.572, "dur": 955.233, + "args": { + "External id": 1415035,"Record function id": 0, "Ev Idx": 17855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533997441.728, "dur": 10.821, + "args": { + "External id": 1415036,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533997466.391, "dur": 38.207, + "args": { + "External id": 1415037,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997472.548, "dur": 2.365, + "args": { + "External id": 1415038,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997478.363, "dur": 0.486, + "args": { + "External id": 1415039,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997480.406, "dur": 0.475, + "args": { + "External id": 1415040,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997482.343, "dur": 0.460, + "args": { + "External id": 1415041,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997486.110, "dur": 0.318, + "args": { + "External id": 1415042,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997487.609, "dur": 0.635, + "args": { + "External id": 1415043,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997489.521, "dur": 4.675, + "args": { + "External id": 1415044,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997495.164, "dur": 0.606, + "args": { + "External id": 1415045,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997497.716, "dur": 0.320, + "args": { + "External id": 1415046,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533997516.962, "dur": 58.574, + "args": { + "External id": 1415047,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410533997609.276, "dur": 122.752, + "args": { + "External id": 1415048,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533997620.706, "dur": 3.711, + "args": { + "External id": 1415049,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410533997629.934, "dur": 9.793, + "args": { + "External id": 1415050,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410533997634.335, "dur": 5.006, + "args": { + "External id": 1415051,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997637.728, "dur": 0.469, + "args": { + "External id": 1415052,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410533997646.269, "dur": 29.862, + "args": { + "External id": 1415053,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997648.162, "dur": 2.339, + "args": { + "External id": 1415054,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997651.769, "dur": 0.416, + "args": { + "External id": 1415055,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997653.658, "dur": 0.531, + "args": { + "External id": 1415056,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997657.699, "dur": 2.858, + "args": { + "External id": 1415057,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997662.163, "dur": 0.385, + "args": { + "External id": 1415058,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997663.720, "dur": 0.414, + "args": { + "External id": 1415059,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997667.126, "dur": 0.454, + "args": { + "External id": 1415060,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997668.779, "dur": 0.401, + "args": { + "External id": 1415061,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533997670.425, "dur": 1.671, + "args": { + "External id": 1415062,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533997688.948, "dur": 35.322, + "args": { + "External id": 1415063,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410533997788.057, "dur": 400.087, + "args": { + "External id": 1415064,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533997819.784, "dur": 362.556, + "args": { + "External id": 1415065,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17885, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410533997830.315, "dur": 343.573, + "args": { + "External id": 1415066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410533998216.085, "dur": 2.721, + "args": { + "External id": 1415067,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17887, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338710, "tid": 2338710, + "ts": 6410533998312.372, "dur": 30096.893, + "args": { + "External id": 1415068,"Record function id": 0, "Ev Idx": 17888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998433.446, "dur": 6.770, + "args": { + "External id": 1415069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998445.331, "dur": 1.424, + "args": { + "External id": 1415070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998448.670, "dur": 3.167, + "args": { + "External id": 1415071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998453.449, "dur": 0.988, + "args": { + "External id": 1415072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998456.012, "dur": 0.932, + "args": { + "External id": 1415073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998458.236, "dur": 3.590, + "args": { + "External id": 1415074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998463.674, "dur": 0.637, + "args": { + "External id": 1415075,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998466.256, "dur": 2.362, + "args": { + "External id": 1415076,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998469.983, "dur": 0.898, + "args": { + "External id": 1415077,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410533998472.558, "dur": 1.083, + "args": { + "External id": 1415078,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533998500.228, "dur": 29845.903, + "args": { + "External id": 1415079,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533998516.250, "dur": 29817.967, + "args": { + "External id": 1415080,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410533998530.770, "dur": 16.663, + "args": { + "External id": 1415081,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410533998551.169, "dur": 29739.244, + "args": { + "External id": 1415082,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410533998553.719, "dur": 29735.601, + "args": { + "External id": 1415083,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410533998560.098, "dur": 5.590, + "args": { + "External id": 1415084,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410533998567.410, "dur": 29717.050, + "args": { + "External id": 1415085,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534028578.226, "dur": 38.566, + "args": { + "External id": 1415086,"Sequence number": 15109106, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17906 + } + }, + { + "ph": "s", "id": 413, "pid": 2338710, "tid": 2338710, "ts": 6410534028578.226, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534028600.378, "dur": 11.706, + "args": { + "External id": 1415087,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534028605.332, "dur": 6.411, + "args": { + "External id": 1415088,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534028688.162, "dur": 69.890, + "args": { + "External id": 1415089,"Record function id": 0, "Ev Idx": 17909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534028759.509, "dur": 1133.747, + "args": { + "External id": 1415090,"Record function id": 0, "Ev Idx": 17910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534028799.933, "dur": 1079.714, + "args": { + "External id": 1415091,"Sequence number": 15109107, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17911 + } + }, + { + "ph": "s", "id": 412, "pid": 2338710, "tid": 2338710, "ts": 6410534028799.933, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534028867.673, "dur": 52.770, + "args": { + "External id": 1415092,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534028933.038, "dur": 103.427, + "args": { + "External id": 1415093,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534029048.802, "dur": 78.049, + "args": { + "External id": 1415094,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534029140.367, "dur": 32.385, + "args": { + "External id": 1415095,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534029202.844, "dur": 29.054, + "args": { + "External id": 1415096,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534029254.209, "dur": 18.633, + "args": { + "External id": 1415097,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534029296.348, "dur": 147.563, + "args": { + "External id": 1415098,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534029346.615, "dur": 12.032, + "args": { + "External id": 1415099,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534029352.529, "dur": 5.283, + "args": { + "External id": 1415100,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534029361.296, "dur": 4.563, + "args": { + "External id": 1415101,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534029367.085, "dur": 1.474, + "args": { + "External id": 1415102,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534029370.943, "dur": 4.663, + "args": { + "External id": 1415103,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534029456.540, "dur": 56.920, + "args": { + "External id": 1415104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534029548.684, "dur": 31.367, + "args": { + "External id": 1415105,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534029589.074, "dur": 43.525, + "args": { + "External id": 1415106,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534029642.819, "dur": 35.294, + "args": { + "External id": 1415107,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534029702.475, "dur": 28.347, + "args": { + "External id": 1415108,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534029738.699, "dur": 37.017, + "args": { + "External id": 1415109,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534029793.063, "dur": 19.515, + "args": { + "External id": 1415110,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17930 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.17)", "pid": 2338710, "tid": 2338710, + "ts": 6410534029957.835, "dur": 78.672, + "args": { + "External id": 1415111,"Record function id": 0, "Ev Idx": 17931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410534030152.272, "dur": 53.945, + "args": { + "External id": 1415112,"Record function id": 0, "Ev Idx": 17932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 2338710, "tid": 2338710, + "ts": 6410534030215.798, "dur": 32298.322, + "args": { + "External id": 1415113,"Record function id": 0, "Ev Idx": 17933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338710, "tid": 2338710, + "ts": 6410534030225.267, "dur": 929.145, + "args": { + "External id": 1415114,"Record function id": 0, "Ev Idx": 17934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534030310.859, "dur": 9.357, + "args": { + "External id": 1415115,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534030332.615, "dur": 37.235, + "args": { + "External id": 1415116,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030339.123, "dur": 2.389, + "args": { + "External id": 1415117,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030345.178, "dur": 0.421, + "args": { + "External id": 1415118,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030347.288, "dur": 0.396, + "args": { + "External id": 1415119,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030349.251, "dur": 0.545, + "args": { + "External id": 1415120,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030352.865, "dur": 0.590, + "args": { + "External id": 1415121,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030354.555, "dur": 0.451, + "args": { + "External id": 1415122,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030356.674, "dur": 2.566, + "args": { + "External id": 1415123,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030360.661, "dur": 0.551, + "args": { + "External id": 1415124,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030362.807, "dur": 0.365, + "args": { + "External id": 1415125,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534030381.784, "dur": 72.430, + "args": { + "External id": 1415126,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410534030494.514, "dur": 119.955, + "args": { + "External id": 1415127,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534030506.209, "dur": 6.876, + "args": { + "External id": 1415128,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410534030519.013, "dur": 11.242, + "args": { + "External id": 1415129,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534030523.549, "dur": 6.319, + "args": { + "External id": 1415130,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030527.632, "dur": 0.589, + "args": { + "External id": 1415131,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534030537.225, "dur": 24.928, + "args": { + "External id": 1415132,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030539.114, "dur": 0.307, + "args": { + "External id": 1415133,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030541.256, "dur": 1.966, + "args": { + "External id": 1415134,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030544.452, "dur": 0.624, + "args": { + "External id": 1415135,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030546.102, "dur": 2.401, + "args": { + "External id": 1415136,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030549.796, "dur": 0.422, + "args": { + "External id": 1415137,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030551.310, "dur": 0.282, + "args": { + "External id": 1415138,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030552.482, "dur": 0.393, + "args": { + "External id": 1415139,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030555.601, "dur": 0.464, + "args": { + "External id": 1415140,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534030556.829, "dur": 0.395, + "args": { + "External id": 1415141,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534030574.123, "dur": 32.262, + "args": { + "External id": 1415142,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410534030668.745, "dur": 346.690, + "args": { + "External id": 1415143,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534030699.243, "dur": 311.375, + "args": { + "External id": 1415144,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17964, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410534030709.395, "dur": 295.762, + "args": { + "External id": 1415145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534031040.309, "dur": 2.380, + "args": { + "External id": 1415146,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 17966, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338710, "tid": 2338710, + "ts": 6410534031176.109, "dur": 31097.597, + "args": { + "External id": 1415147,"Record function id": 0, "Ev Idx": 17967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031279.713, "dur": 6.849, + "args": { + "External id": 1415148,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031289.979, "dur": 1.128, + "args": { + "External id": 1415149,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031292.752, "dur": 3.729, + "args": { + "External id": 1415150,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031298.146, "dur": 1.050, + "args": { + "External id": 1415151,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031300.586, "dur": 0.895, + "args": { + "External id": 1415152,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031302.592, "dur": 1.036, + "args": { + "External id": 1415153,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031305.353, "dur": 0.971, + "args": { + "External id": 1415154,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031308.077, "dur": 2.172, + "args": { + "External id": 1415155,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031311.757, "dur": 0.824, + "args": { + "External id": 1415156,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534031315.884, "dur": 0.918, + "args": { + "External id": 1415157,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534031334.655, "dur": 30875.418, + "args": { + "External id": 1415158,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534031351.522, "dur": 30846.823, + "args": { + "External id": 1415159,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534031366.350, "dur": 16.171, + "args": { + "External id": 1415160,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534031385.986, "dur": 30766.335, + "args": { + "External id": 1415161,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534031388.603, "dur": 30762.592, + "args": { + "External id": 1415162,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534031394.727, "dur": 6.150, + "args": { + "External id": 1415163,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534031402.531, "dur": 30743.666, + "args": { + "External id": 1415164,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534062446.015, "dur": 37.081, + "args": { + "External id": 1415165,"Sequence number": 15109108, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17985 + } + }, + { + "ph": "s", "id": 411, "pid": 2338710, "tid": 2338710, "ts": 6410534062446.015, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534062466.540, "dur": 11.762, + "args": { + "External id": 1415166,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534062471.350, "dur": 6.623, + "args": { + "External id": 1415167,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534062555.789, "dur": 73.767, + "args": { + "External id": 1415168,"Record function id": 0, "Ev Idx": 17988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534062654.690, "dur": 1134.057, + "args": { + "External id": 1415169,"Record function id": 0, "Ev Idx": 17989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534062695.269, "dur": 1079.529, + "args": { + "External id": 1415170,"Sequence number": 15109109, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17990 + } + }, + { + "ph": "s", "id": 410, "pid": 2338710, "tid": 2338710, "ts": 6410534062695.269, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534062764.205, "dur": 54.548, + "args": { + "External id": 1415171,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534062831.233, "dur": 106.084, + "args": { + "External id": 1415172,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534062951.035, "dur": 42.314, + "args": { + "External id": 1415173,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534063001.022, "dur": 29.871, + "args": { + "External id": 1415174,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534063096.500, "dur": 31.089, + "args": { + "External id": 1415175,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534063152.998, "dur": 17.031, + "args": { + "External id": 1415176,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534063194.468, "dur": 131.770, + "args": { + "External id": 1415177,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534063245.791, "dur": 12.526, + "args": { + "External id": 1415178,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534063251.471, "dur": 5.985, + "args": { + "External id": 1415179,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534063261.218, "dur": 4.394, + "args": { + "External id": 1415180,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534063267.307, "dur": 0.966, + "args": { + "External id": 1415181,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534063272.285, "dur": 4.888, + "args": { + "External id": 1415182,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534063336.789, "dur": 54.206, + "args": { + "External id": 1415183,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534063439.176, "dur": 32.455, + "args": { + "External id": 1415184,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534063483.880, "dur": 46.992, + "args": { + "External id": 1415185,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534063540.677, "dur": 35.614, + "args": { + "External id": 1415186,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534063600.713, "dur": 28.469, + "args": { + "External id": 1415187,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534063635.218, "dur": 36.907, + "args": { + "External id": 1415188,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534063690.852, "dur": 17.612, + "args": { + "External id": 1415189,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18009 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.18)", "pid": 2338710, "tid": 2338710, + "ts": 6410534063854.983, "dur": 81.183, + "args": { + "External id": 1415190,"Record function id": 0, "Ev Idx": 18010 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410534064010.835, "dur": 85.643, + "args": { + "External id": 1415191,"Record function id": 0, "Ev Idx": 18011 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 2338710, "tid": 2338710, + "ts": 6410534064108.685, "dur": 31144.442, + "args": { + "External id": 1415192,"Record function id": 0, "Ev Idx": 18012 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338710, "tid": 2338710, + "ts": 6410534064117.960, "dur": 921.662, + "args": { + "External id": 1415193,"Record function id": 0, "Ev Idx": 18013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534064205.037, "dur": 9.748, + "args": { + "External id": 1415194,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534064228.147, "dur": 40.614, + "args": { + "External id": 1415195,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064234.209, "dur": 2.426, + "args": { + "External id": 1415196,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064240.005, "dur": 0.452, + "args": { + "External id": 1415197,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064242.598, "dur": 0.855, + "args": { + "External id": 1415198,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064244.516, "dur": 0.584, + "args": { + "External id": 1415199,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064248.433, "dur": 0.462, + "args": { + "External id": 1415200,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064250.397, "dur": 0.669, + "args": { + "External id": 1415201,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064252.887, "dur": 4.292, + "args": { + "External id": 1415202,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064258.644, "dur": 0.603, + "args": { + "External id": 1415203,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064261.118, "dur": 0.556, + "args": { + "External id": 1415204,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534064281.410, "dur": 52.836, + "args": { + "External id": 1415205,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410534064367.811, "dur": 153.990, + "args": { + "External id": 1415206,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534064379.757, "dur": 4.505, + "args": { + "External id": 1415207,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410534064393.878, "dur": 10.497, + "args": { + "External id": 1415208,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534064398.480, "dur": 5.460, + "args": { + "External id": 1415209,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064402.110, "dur": 0.648, + "args": { + "External id": 1415210,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534064411.454, "dur": 46.408, + "args": { + "External id": 1415211,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064413.851, "dur": 16.301, + "args": { + "External id": 1415212,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064432.929, "dur": 0.316, + "args": { + "External id": 1415213,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064435.335, "dur": 0.480, + "args": { + "External id": 1415214,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064439.007, "dur": 2.431, + "args": { + "External id": 1415215,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064442.490, "dur": 0.532, + "args": { + "External id": 1415216,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064444.687, "dur": 0.374, + "args": { + "External id": 1415217,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064448.131, "dur": 0.416, + "args": { + "External id": 1415218,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064449.974, "dur": 0.553, + "args": { + "External id": 1415219,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534064452.040, "dur": 1.551, + "args": { + "External id": 1415220,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534064476.100, "dur": 36.834, + "args": { + "External id": 1415221,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410534064580.869, "dur": 363.299, + "args": { + "External id": 1415222,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534064613.339, "dur": 325.993, + "args": { + "External id": 1415223,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18043, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410534064624.726, "dur": 308.668, + "args": { + "External id": 1415224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534064969.038, "dur": 2.219, + "args": { + "External id": 1415225,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 18045, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338710, "tid": 2338710, + "ts": 6410534065095.675, "dur": 29902.490, + "args": { + "External id": 1415226,"Record function id": 0, "Ev Idx": 18046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065205.528, "dur": 7.313, + "args": { + "External id": 1415227,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065216.550, "dur": 0.979, + "args": { + "External id": 1415228,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065219.401, "dur": 4.036, + "args": { + "External id": 1415229,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065225.589, "dur": 0.813, + "args": { + "External id": 1415230,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065227.850, "dur": 0.943, + "args": { + "External id": 1415231,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065230.158, "dur": 1.171, + "args": { + "External id": 1415232,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065232.897, "dur": 0.819, + "args": { + "External id": 1415233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065235.538, "dur": 2.064, + "args": { + "External id": 1415234,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065238.721, "dur": 0.848, + "args": { + "External id": 1415235,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534065243.061, "dur": 0.868, + "args": { + "External id": 1415236,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534065262.534, "dur": 29671.480, + "args": { + "External id": 1415237,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534065278.882, "dur": 29643.073, + "args": { + "External id": 1415238,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534065298.362, "dur": 16.910, + "args": { + "External id": 1415239,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534065318.875, "dur": 29558.196, + "args": { + "External id": 1415240,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534065321.661, "dur": 29554.370, + "args": { + "External id": 1415241,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534065327.056, "dur": 5.658, + "args": { + "External id": 1415242,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534065334.455, "dur": 29536.855, + "args": { + "External id": 1415243,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534095186.888, "dur": 36.200, + "args": { + "External id": 1415244,"Sequence number": 15109110, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18064 + } + }, + { + "ph": "s", "id": 409, "pid": 2338710, "tid": 2338710, "ts": 6410534095186.888, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534095205.877, "dur": 12.169, + "args": { + "External id": 1415245,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534095211.099, "dur": 6.657, + "args": { + "External id": 1415246,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534095294.190, "dur": 70.799, + "args": { + "External id": 1415247,"Record function id": 0, "Ev Idx": 18067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534095366.447, "dur": 1120.072, + "args": { + "External id": 1415248,"Record function id": 0, "Ev Idx": 18068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534095405.059, "dur": 1067.214, + "args": { + "External id": 1415249,"Sequence number": 15109111, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18069 + } + }, + { + "ph": "s", "id": 408, "pid": 2338710, "tid": 2338710, "ts": 6410534095405.059, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534095486.827, "dur": 52.294, + "args": { + "External id": 1415250,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534095552.393, "dur": 102.048, + "args": { + "External id": 1415251,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534095666.374, "dur": 38.914, + "args": { + "External id": 1415252,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534095714.709, "dur": 31.090, + "args": { + "External id": 1415253,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534095772.211, "dur": 27.142, + "args": { + "External id": 1415254,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534095821.633, "dur": 16.823, + "args": { + "External id": 1415255,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534095860.969, "dur": 128.340, + "args": { + "External id": 1415256,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534095910.814, "dur": 11.122, + "args": { + "External id": 1415257,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534095915.466, "dur": 5.636, + "args": { + "External id": 1415258,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534095924.501, "dur": 4.423, + "args": { + "External id": 1415259,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534095930.247, "dur": 1.229, + "args": { + "External id": 1415260,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534095933.895, "dur": 5.510, + "args": { + "External id": 1415261,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534095999.877, "dur": 48.105, + "args": { + "External id": 1415262,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534096119.393, "dur": 31.527, + "args": { + "External id": 1415263,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534096161.574, "dur": 48.901, + "args": { + "External id": 1415264,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534096221.582, "dur": 35.315, + "args": { + "External id": 1415265,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534096281.667, "dur": 31.209, + "args": { + "External id": 1415266,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534096320.549, "dur": 36.831, + "args": { + "External id": 1415267,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534096375.379, "dur": 16.843, + "args": { + "External id": 1415268,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18088 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.19)", "pid": 2338710, "tid": 2338710, + "ts": 6410534096552.830, "dur": 80.180, + "args": { + "External id": 1415269,"Record function id": 0, "Ev Idx": 18089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410534096709.958, "dur": 47.612, + "args": { + "External id": 1415270,"Record function id": 0, "Ev Idx": 18090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 2338710, "tid": 2338710, + "ts": 6410534096766.631, "dur": 31845.503, + "args": { + "External id": 1415271,"Record function id": 0, "Ev Idx": 18091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338710, "tid": 2338710, + "ts": 6410534096774.208, "dur": 1000.710, + "args": { + "External id": 1415272,"Record function id": 0, "Ev Idx": 18092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534096861.354, "dur": 8.775, + "args": { + "External id": 1415273,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534096883.544, "dur": 37.202, + "args": { + "External id": 1415274,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096889.519, "dur": 2.345, + "args": { + "External id": 1415275,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096895.689, "dur": 0.590, + "args": { + "External id": 1415276,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096897.499, "dur": 0.452, + "args": { + "External id": 1415277,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096899.351, "dur": 0.666, + "args": { + "External id": 1415278,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096903.330, "dur": 0.582, + "args": { + "External id": 1415279,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096905.546, "dur": 0.501, + "args": { + "External id": 1415280,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096907.653, "dur": 3.871, + "args": { + "External id": 1415281,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096912.579, "dur": 0.435, + "args": { + "External id": 1415282,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534096914.409, "dur": 0.542, + "args": { + "External id": 1415283,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534096932.844, "dur": 55.317, + "args": { + "External id": 1415284,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410534097020.902, "dur": 187.312, + "args": { + "External id": 1415285,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534097032.418, "dur": 3.993, + "args": { + "External id": 1415286,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410534097042.191, "dur": 64.133, + "args": { + "External id": 1415287,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534097046.811, "dur": 58.989, + "args": { + "External id": 1415288,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097101.810, "dur": 1.308, + "args": { + "External id": 1415289,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534097117.020, "dur": 29.630, + "args": { + "External id": 1415290,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097119.982, "dur": 2.451, + "args": { + "External id": 1415291,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097123.864, "dur": 0.680, + "args": { + "External id": 1415292,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097125.572, "dur": 0.303, + "args": { + "External id": 1415293,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097128.517, "dur": 2.303, + "args": { + "External id": 1415294,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097132.006, "dur": 0.452, + "args": { + "External id": 1415295,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097133.764, "dur": 0.455, + "args": { + "External id": 1415296,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097136.986, "dur": 0.595, + "args": { + "External id": 1415297,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097139.086, "dur": 0.443, + "args": { + "External id": 1415298,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534097140.273, "dur": 2.075, + "args": { + "External id": 1415299,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534097159.221, "dur": 40.206, + "args": { + "External id": 1415300,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410534097266.373, "dur": 403.994, + "args": { + "External id": 1415301,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534097298.435, "dur": 366.577, + "args": { + "External id": 1415302,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18122, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410534097308.849, "dur": 350.050, + "args": { + "External id": 1415303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534097698.302, "dur": 2.630, + "args": { + "External id": 1415304,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 18124, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338710, "tid": 2338710, + "ts": 6410534097796.198, "dur": 30580.611, + "args": { + "External id": 1415305,"Record function id": 0, "Ev Idx": 18125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097904.284, "dur": 6.985, + "args": { + "External id": 1415306,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097914.549, "dur": 0.970, + "args": { + "External id": 1415307,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097917.119, "dur": 3.107, + "args": { + "External id": 1415308,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097921.846, "dur": 0.662, + "args": { + "External id": 1415309,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097923.797, "dur": 1.166, + "args": { + "External id": 1415310,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097926.026, "dur": 0.780, + "args": { + "External id": 1415311,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097928.344, "dur": 0.992, + "args": { + "External id": 1415312,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097930.679, "dur": 1.866, + "args": { + "External id": 1415313,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097934.206, "dur": 1.095, + "args": { + "External id": 1415314,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534097938.342, "dur": 1.093, + "args": { + "External id": 1415315,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534097956.823, "dur": 30360.318, + "args": { + "External id": 1415316,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534097972.201, "dur": 30333.503, + "args": { + "External id": 1415317,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534097990.053, "dur": 15.601, + "args": { + "External id": 1415318,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534098009.206, "dur": 30251.939, + "args": { + "External id": 1415319,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534098011.718, "dur": 30248.249, + "args": { + "External id": 1415320,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534098017.957, "dur": 5.989, + "args": { + "External id": 1415321,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534098025.602, "dur": 30229.563, + "args": { + "External id": 1415322,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534128548.011, "dur": 36.288, + "args": { + "External id": 1415323,"Sequence number": 15109112, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18143 + } + }, + { + "ph": "s", "id": 407, "pid": 2338710, "tid": 2338710, "ts": 6410534128548.011, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534128567.601, "dur": 11.995, + "args": { + "External id": 1415324,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534128572.839, "dur": 6.347, + "args": { + "External id": 1415325,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534128651.238, "dur": 68.942, + "args": { + "External id": 1415326,"Record function id": 0, "Ev Idx": 18146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534128721.679, "dur": 1138.647, + "args": { + "External id": 1415327,"Record function id": 0, "Ev Idx": 18147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534128760.829, "dur": 1086.352, + "args": { + "External id": 1415328,"Sequence number": 15109113, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18148 + } + }, + { + "ph": "s", "id": 406, "pid": 2338710, "tid": 2338710, "ts": 6410534128760.829, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534128827.611, "dur": 61.294, + "args": { + "External id": 1415329,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534128901.297, "dur": 102.873, + "args": { + "External id": 1415330,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534129017.003, "dur": 81.365, + "args": { + "External id": 1415331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534129112.259, "dur": 35.095, + "args": { + "External id": 1415332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534129175.950, "dur": 27.717, + "args": { + "External id": 1415333,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534129225.643, "dur": 16.860, + "args": { + "External id": 1415334,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534129265.677, "dur": 129.361, + "args": { + "External id": 1415335,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534129314.941, "dur": 12.066, + "args": { + "External id": 1415336,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534129320.643, "dur": 5.600, + "args": { + "External id": 1415337,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534129329.476, "dur": 4.688, + "args": { + "External id": 1415338,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534129335.961, "dur": 0.998, + "args": { + "External id": 1415339,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534129339.283, "dur": 5.644, + "args": { + "External id": 1415340,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534129405.330, "dur": 74.809, + "args": { + "External id": 1415341,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534129516.724, "dur": 33.475, + "args": { + "External id": 1415342,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534129560.197, "dur": 43.238, + "args": { + "External id": 1415343,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534129614.454, "dur": 35.749, + "args": { + "External id": 1415344,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534129673.647, "dur": 29.328, + "args": { + "External id": 1415345,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534129710.311, "dur": 36.454, + "args": { + "External id": 1415346,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534129764.636, "dur": 17.747, + "args": { + "External id": 1415347,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18167 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.20)", "pid": 2338710, "tid": 2338710, + "ts": 6410534129925.993, "dur": 81.004, + "args": { + "External id": 1415348,"Record function id": 0, "Ev Idx": 18168 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410534130124.156, "dur": 52.502, + "args": { + "External id": 1415349,"Record function id": 0, "Ev Idx": 18169 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 2338710, "tid": 2338710, + "ts": 6410534130186.942, "dur": 32456.284, + "args": { + "External id": 1415350,"Record function id": 0, "Ev Idx": 18170 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338710, "tid": 2338710, + "ts": 6410534130195.342, "dur": 952.361, + "args": { + "External id": 1415351,"Record function id": 0, "Ev Idx": 18171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534130285.582, "dur": 10.247, + "args": { + "External id": 1415352,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534130308.705, "dur": 38.681, + "args": { + "External id": 1415353,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130315.103, "dur": 2.397, + "args": { + "External id": 1415354,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130321.373, "dur": 0.517, + "args": { + "External id": 1415355,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130323.660, "dur": 0.725, + "args": { + "External id": 1415356,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130325.377, "dur": 0.432, + "args": { + "External id": 1415357,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130329.024, "dur": 0.686, + "args": { + "External id": 1415358,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130331.224, "dur": 0.638, + "args": { + "External id": 1415359,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130333.386, "dur": 4.152, + "args": { + "External id": 1415360,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130338.774, "dur": 0.499, + "args": { + "External id": 1415361,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130341.177, "dur": 0.609, + "args": { + "External id": 1415362,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534130359.223, "dur": 72.032, + "args": { + "External id": 1415363,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410534130469.331, "dur": 127.526, + "args": { + "External id": 1415364,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534130481.214, "dur": 4.827, + "args": { + "External id": 1415365,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410534130493.615, "dur": 10.799, + "args": { + "External id": 1415366,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534130498.124, "dur": 5.909, + "args": { + "External id": 1415367,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130501.942, "dur": 0.541, + "args": { + "External id": 1415368,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534130511.157, "dur": 28.620, + "args": { + "External id": 1415369,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130513.066, "dur": 2.239, + "args": { + "External id": 1415370,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130516.652, "dur": 0.750, + "args": { + "External id": 1415371,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130519.239, "dur": 0.704, + "args": { + "External id": 1415372,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130522.855, "dur": 2.556, + "args": { + "External id": 1415373,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130526.690, "dur": 0.492, + "args": { + "External id": 1415374,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130528.863, "dur": 0.266, + "args": { + "External id": 1415375,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130531.117, "dur": 0.451, + "args": { + "External id": 1415376,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130532.770, "dur": 0.440, + "args": { + "External id": 1415377,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534130534.351, "dur": 1.711, + "args": { + "External id": 1415378,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534130553.445, "dur": 35.526, + "args": { + "External id": 1415379,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410534130654.013, "dur": 357.895, + "args": { + "External id": 1415380,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534130686.188, "dur": 320.640, + "args": { + "External id": 1415381,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18201, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410534130696.338, "dur": 305.199, + "args": { + "External id": 1415382,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534131034.835, "dur": 2.276, + "args": { + "External id": 1415383,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 18203, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338710, "tid": 2338710, + "ts": 6410534131170.468, "dur": 31232.344, + "args": { + "External id": 1415384,"Record function id": 0, "Ev Idx": 18204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131275.284, "dur": 7.055, + "args": { + "External id": 1415385,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131285.659, "dur": 1.105, + "args": { + "External id": 1415386,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131288.359, "dur": 3.357, + "args": { + "External id": 1415387,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131293.404, "dur": 0.965, + "args": { + "External id": 1415388,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131295.527, "dur": 0.799, + "args": { + "External id": 1415389,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131297.782, "dur": 0.676, + "args": { + "External id": 1415390,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131299.994, "dur": 1.044, + "args": { + "External id": 1415391,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131302.892, "dur": 2.019, + "args": { + "External id": 1415392,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131306.281, "dur": 1.047, + "args": { + "External id": 1415393,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534131311.146, "dur": 0.635, + "args": { + "External id": 1415394,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534131329.315, "dur": 31010.057, + "args": { + "External id": 1415395,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534131344.785, "dur": 30982.788, + "args": { + "External id": 1415396,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534131365.508, "dur": 16.541, + "args": { + "External id": 1415397,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534131385.666, "dur": 30898.059, + "args": { + "External id": 1415398,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534131387.999, "dur": 30894.602, + "args": { + "External id": 1415399,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534131399.456, "dur": 5.764, + "args": { + "External id": 1415400,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534131407.133, "dur": 30870.572, + "args": { + "External id": 1415401,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534162575.872, "dur": 37.834, + "args": { + "External id": 1415402,"Sequence number": 15109114, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18222 + } + }, + { + "ph": "s", "id": 405, "pid": 2338710, "tid": 2338710, "ts": 6410534162575.872, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534162596.855, "dur": 11.941, + "args": { + "External id": 1415403,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534162601.565, "dur": 6.872, + "args": { + "External id": 1415404,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534162685.410, "dur": 69.822, + "args": { + "External id": 1415405,"Record function id": 0, "Ev Idx": 18225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534162756.994, "dur": 1130.146, + "args": { + "External id": 1415406,"Record function id": 0, "Ev Idx": 18226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534162796.941, "dur": 1076.314, + "args": { + "External id": 1415407,"Sequence number": 15109115, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18227 + } + }, + { + "ph": "s", "id": 404, "pid": 2338710, "tid": 2338710, "ts": 6410534162796.941, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534162867.084, "dur": 51.182, + "args": { + "External id": 1415408,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534162931.400, "dur": 101.246, + "args": { + "External id": 1415409,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534163043.883, "dur": 78.794, + "args": { + "External id": 1415410,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534163136.193, "dur": 32.087, + "args": { + "External id": 1415411,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534163197.923, "dur": 27.861, + "args": { + "External id": 1415412,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534163248.196, "dur": 17.694, + "args": { + "External id": 1415413,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534163289.400, "dur": 147.702, + "args": { + "External id": 1415414,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534163341.411, "dur": 11.618, + "args": { + "External id": 1415415,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534163346.972, "dur": 5.054, + "args": { + "External id": 1415416,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534163355.633, "dur": 4.435, + "args": { + "External id": 1415417,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534163361.260, "dur": 1.348, + "args": { + "External id": 1415418,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534163365.204, "dur": 6.295, + "args": { + "External id": 1415419,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534163449.036, "dur": 56.723, + "args": { + "External id": 1415420,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534163538.518, "dur": 32.692, + "args": { + "External id": 1415421,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534163581.106, "dur": 43.126, + "args": { + "External id": 1415422,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534163636.029, "dur": 35.784, + "args": { + "External id": 1415423,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534163697.094, "dur": 29.510, + "args": { + "External id": 1415424,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534163734.528, "dur": 36.682, + "args": { + "External id": 1415425,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534163790.298, "dur": 19.397, + "args": { + "External id": 1415426,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18246 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.21)", "pid": 2338710, "tid": 2338710, + "ts": 6410534163951.510, "dur": 81.125, + "args": { + "External id": 1415427,"Record function id": 0, "Ev Idx": 18247 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410534164150.121, "dur": 49.694, + "args": { + "External id": 1415428,"Record function id": 0, "Ev Idx": 18248 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 2338710, "tid": 2338710, + "ts": 6410534164209.786, "dur": 31082.485, + "args": { + "External id": 1415429,"Record function id": 0, "Ev Idx": 18249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338710, "tid": 2338710, + "ts": 6410534164218.376, "dur": 956.955, + "args": { + "External id": 1415430,"Record function id": 0, "Ev Idx": 18250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534164306.728, "dur": 9.396, + "args": { + "External id": 1415431,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534164329.152, "dur": 38.396, + "args": { + "External id": 1415432,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164335.278, "dur": 2.560, + "args": { + "External id": 1415433,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164342.036, "dur": 0.563, + "args": { + "External id": 1415434,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164344.139, "dur": 0.589, + "args": { + "External id": 1415435,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164346.089, "dur": 0.527, + "args": { + "External id": 1415436,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164349.083, "dur": 0.329, + "args": { + "External id": 1415437,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164351.022, "dur": 0.407, + "args": { + "External id": 1415438,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164352.919, "dur": 4.379, + "args": { + "External id": 1415439,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164358.768, "dur": 0.508, + "args": { + "External id": 1415440,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164360.519, "dur": 0.437, + "args": { + "External id": 1415441,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534164378.903, "dur": 72.578, + "args": { + "External id": 1415442,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410534164489.224, "dur": 133.904, + "args": { + "External id": 1415443,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534164501.111, "dur": 5.145, + "args": { + "External id": 1415444,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410534164511.486, "dur": 10.604, + "args": { + "External id": 1415445,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534164516.050, "dur": 5.654, + "args": { + "External id": 1415446,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164519.539, "dur": 0.568, + "args": { + "External id": 1415447,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534164529.049, "dur": 31.664, + "args": { + "External id": 1415448,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164531.141, "dur": 1.762, + "args": { + "External id": 1415449,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164534.627, "dur": 0.604, + "args": { + "External id": 1415450,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164537.126, "dur": 0.605, + "args": { + "External id": 1415451,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164540.495, "dur": 2.631, + "args": { + "External id": 1415452,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164546.773, "dur": 0.378, + "args": { + "External id": 1415453,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164548.806, "dur": 0.270, + "args": { + "External id": 1415454,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164551.403, "dur": 0.612, + "args": { + "External id": 1415455,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164553.585, "dur": 0.509, + "args": { + "External id": 1415456,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534164555.306, "dur": 1.889, + "args": { + "External id": 1415457,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534164572.432, "dur": 42.426, + "args": { + "External id": 1415458,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410534164679.252, "dur": 357.387, + "args": { + "External id": 1415459,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534164710.908, "dur": 320.701, + "args": { + "External id": 1415460,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18280, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410534164721.078, "dur": 305.357, + "args": { + "External id": 1415461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534165096.700, "dur": 3.983, + "args": { + "External id": 1415462,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 18282, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338710, "tid": 2338710, + "ts": 6410534165196.974, "dur": 29848.237, + "args": { + "External id": 1415463,"Record function id": 0, "Ev Idx": 18283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165301.750, "dur": 6.881, + "args": { + "External id": 1415464,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165311.852, "dur": 1.364, + "args": { + "External id": 1415465,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165314.759, "dur": 3.355, + "args": { + "External id": 1415466,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165319.491, "dur": 0.825, + "args": { + "External id": 1415467,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165321.528, "dur": 0.891, + "args": { + "External id": 1415468,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165323.588, "dur": 0.831, + "args": { + "External id": 1415469,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165326.284, "dur": 0.667, + "args": { + "External id": 1415470,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165328.358, "dur": 1.963, + "args": { + "External id": 1415471,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165331.871, "dur": 0.746, + "args": { + "External id": 1415472,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534165336.039, "dur": 0.644, + "args": { + "External id": 1415473,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534165354.238, "dur": 29630.156, + "args": { + "External id": 1415474,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534165369.515, "dur": 29603.636, + "args": { + "External id": 1415475,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534165386.217, "dur": 15.807, + "args": { + "External id": 1415476,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534165405.624, "dur": 29523.202, + "args": { + "External id": 1415477,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534165407.983, "dur": 29519.833, + "args": { + "External id": 1415478,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534165413.718, "dur": 21.202, + "args": { + "External id": 1415479,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534165437.545, "dur": 29485.410, + "args": { + "External id": 1415480,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534195227.677, "dur": 35.411, + "args": { + "External id": 1415481,"Sequence number": 15109116, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18301 + } + }, + { + "ph": "s", "id": 403, "pid": 2338710, "tid": 2338710, "ts": 6410534195227.677, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534195246.583, "dur": 11.788, + "args": { + "External id": 1415482,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534195251.404, "dur": 6.630, + "args": { + "External id": 1415483,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534195333.103, "dur": 68.718, + "args": { + "External id": 1415484,"Record function id": 0, "Ev Idx": 18304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534195403.223, "dur": 1150.234, + "args": { + "External id": 1415485,"Record function id": 0, "Ev Idx": 18305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534195457.178, "dur": 1082.091, + "args": { + "External id": 1415486,"Sequence number": 15109117, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18306 + } + }, + { + "ph": "s", "id": 402, "pid": 2338710, "tid": 2338710, "ts": 6410534195457.178, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534195526.196, "dur": 56.298, + "args": { + "External id": 1415487,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534195595.700, "dur": 106.319, + "args": { + "External id": 1415488,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534195714.871, "dur": 40.804, + "args": { + "External id": 1415489,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534195764.490, "dur": 30.289, + "args": { + "External id": 1415490,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534195821.077, "dur": 28.022, + "args": { + "External id": 1415491,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534195870.230, "dur": 18.381, + "args": { + "External id": 1415492,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534195910.974, "dur": 133.960, + "args": { + "External id": 1415493,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534195962.862, "dur": 12.157, + "args": { + "External id": 1415494,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534195968.399, "dur": 5.752, + "args": { + "External id": 1415495,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534195977.852, "dur": 4.093, + "args": { + "External id": 1415496,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534195983.447, "dur": 1.356, + "args": { + "External id": 1415497,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534195987.169, "dur": 5.709, + "args": { + "External id": 1415498,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534196094.664, "dur": 58.731, + "args": { + "External id": 1415499,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534196189.014, "dur": 30.750, + "args": { + "External id": 1415500,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534196229.562, "dur": 42.403, + "args": { + "External id": 1415501,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534196282.077, "dur": 35.390, + "args": { + "External id": 1415502,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534196340.815, "dur": 29.454, + "args": { + "External id": 1415503,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534196376.871, "dur": 36.947, + "args": { + "External id": 1415504,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534196451.450, "dur": 22.087, + "args": { + "External id": 1415505,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18325 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.22)", "pid": 2338710, "tid": 2338710, + "ts": 6410534196621.425, "dur": 77.571, + "args": { + "External id": 1415506,"Record function id": 0, "Ev Idx": 18326 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410534196773.143, "dur": 47.452, + "args": { + "External id": 1415507,"Record function id": 0, "Ev Idx": 18327 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 2338710, "tid": 2338710, + "ts": 6410534196829.917, "dur": 32013.376, + "args": { + "External id": 1415508,"Record function id": 0, "Ev Idx": 18328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338710, "tid": 2338710, + "ts": 6410534196837.746, "dur": 966.162, + "args": { + "External id": 1415509,"Record function id": 0, "Ev Idx": 18329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534196924.135, "dur": 9.144, + "args": { + "External id": 1415510,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534196945.259, "dur": 36.895, + "args": { + "External id": 1415511,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196951.292, "dur": 2.282, + "args": { + "External id": 1415512,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196956.959, "dur": 0.498, + "args": { + "External id": 1415513,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196959.052, "dur": 0.621, + "args": { + "External id": 1415514,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196960.666, "dur": 0.594, + "args": { + "External id": 1415515,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196964.413, "dur": 0.301, + "args": { + "External id": 1415516,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196965.985, "dur": 0.376, + "args": { + "External id": 1415517,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196969.986, "dur": 3.145, + "args": { + "External id": 1415518,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196974.016, "dur": 0.505, + "args": { + "External id": 1415519,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534196976.108, "dur": 0.312, + "args": { + "External id": 1415520,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534196993.954, "dur": 54.805, + "args": { + "External id": 1415521,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410534197137.141, "dur": 131.381, + "args": { + "External id": 1415522,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534197149.088, "dur": 6.741, + "args": { + "External id": 1415523,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410534197161.376, "dur": 11.899, + "args": { + "External id": 1415524,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534197166.092, "dur": 6.773, + "args": { + "External id": 1415525,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197170.312, "dur": 0.699, + "args": { + "External id": 1415526,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534197180.779, "dur": 26.695, + "args": { + "External id": 1415527,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197182.979, "dur": 1.688, + "args": { + "External id": 1415528,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197186.083, "dur": 0.528, + "args": { + "External id": 1415529,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197187.653, "dur": 0.357, + "args": { + "External id": 1415530,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197190.563, "dur": 2.457, + "args": { + "External id": 1415531,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197194.199, "dur": 0.315, + "args": { + "External id": 1415532,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197196.060, "dur": 0.318, + "args": { + "External id": 1415533,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197198.142, "dur": 0.552, + "args": { + "External id": 1415534,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197200.327, "dur": 0.348, + "args": { + "External id": 1415535,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534197201.628, "dur": 1.685, + "args": { + "External id": 1415536,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534197220.899, "dur": 39.688, + "args": { + "External id": 1415537,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410534197327.239, "dur": 373.510, + "args": { + "External id": 1415538,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534197357.443, "dur": 337.465, + "args": { + "External id": 1415539,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18359, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410534197368.134, "dur": 320.934, + "args": { + "External id": 1415540,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534197729.705, "dur": 2.583, + "args": { + "External id": 1415541,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 18361, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338710, "tid": 2338710, + "ts": 6410534197825.990, "dur": 30791.252, + "args": { + "External id": 1415542,"Record function id": 0, "Ev Idx": 18362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197932.191, "dur": 6.460, + "args": { + "External id": 1415543,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197942.116, "dur": 1.292, + "args": { + "External id": 1415544,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197945.168, "dur": 3.893, + "args": { + "External id": 1415545,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197950.517, "dur": 0.604, + "args": { + "External id": 1415546,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197952.188, "dur": 1.147, + "args": { + "External id": 1415547,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197954.511, "dur": 1.012, + "args": { + "External id": 1415548,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197956.951, "dur": 0.644, + "args": { + "External id": 1415549,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197959.335, "dur": 1.861, + "args": { + "External id": 1415550,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197962.399, "dur": 0.849, + "args": { + "External id": 1415551,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534197966.523, "dur": 0.532, + "args": { + "External id": 1415552,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534197985.475, "dur": 30570.302, + "args": { + "External id": 1415553,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534198001.311, "dur": 30542.692, + "args": { + "External id": 1415554,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534198017.878, "dur": 16.048, + "args": { + "External id": 1415555,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534198037.320, "dur": 30460.831, + "args": { + "External id": 1415556,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534198039.997, "dur": 30457.094, + "args": { + "External id": 1415557,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534198045.245, "dur": 5.538, + "args": { + "External id": 1415558,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534198087.383, "dur": 30404.318, + "args": { + "External id": 1415559,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534228778.596, "dur": 34.994, + "args": { + "External id": 1415560,"Sequence number": 15109118, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18380 + } + }, + { + "ph": "s", "id": 401, "pid": 2338710, "tid": 2338710, "ts": 6410534228778.596, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534228797.497, "dur": 11.343, + "args": { + "External id": 1415561,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534228802.368, "dur": 6.285, + "args": { + "External id": 1415562,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534228883.296, "dur": 70.772, + "args": { + "External id": 1415563,"Record function id": 0, "Ev Idx": 18383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534228955.439, "dur": 1159.278, + "args": { + "External id": 1415564,"Record function id": 0, "Ev Idx": 18384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534228993.496, "dur": 1104.822, + "args": { + "External id": 1415565,"Sequence number": 15109119, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18385 + } + }, + { + "ph": "s", "id": 400, "pid": 2338710, "tid": 2338710, "ts": 6410534228993.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534229092.236, "dur": 54.780, + "args": { + "External id": 1415566,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534229162.019, "dur": 104.367, + "args": { + "External id": 1415567,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534229278.741, "dur": 38.006, + "args": { + "External id": 1415568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534229325.609, "dur": 29.902, + "args": { + "External id": 1415569,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534229383.627, "dur": 26.939, + "args": { + "External id": 1415570,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534229449.400, "dur": 21.083, + "args": { + "External id": 1415571,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534229494.169, "dur": 134.063, + "args": { + "External id": 1415572,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534229545.036, "dur": 11.614, + "args": { + "External id": 1415573,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534229550.216, "dur": 5.702, + "args": { + "External id": 1415574,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534229559.108, "dur": 4.243, + "args": { + "External id": 1415575,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534229564.641, "dur": 1.326, + "args": { + "External id": 1415576,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534229568.776, "dur": 5.473, + "args": { + "External id": 1415577,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534229639.098, "dur": 53.593, + "args": { + "External id": 1415578,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534229725.029, "dur": 33.162, + "args": { + "External id": 1415579,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534229768.791, "dur": 43.659, + "args": { + "External id": 1415580,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534229822.837, "dur": 35.813, + "args": { + "External id": 1415581,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534229883.397, "dur": 30.498, + "args": { + "External id": 1415582,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534229921.843, "dur": 38.288, + "args": { + "External id": 1415583,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534229978.471, "dur": 19.198, + "args": { + "External id": 1415584,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18404 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.23)", "pid": 2338710, "tid": 2338710, + "ts": 6410534230182.738, "dur": 82.767, + "args": { + "External id": 1415585,"Record function id": 0, "Ev Idx": 18405 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410534230339.378, "dur": 47.049, + "args": { + "External id": 1415586,"Record function id": 0, "Ev Idx": 18406 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 2338710, "tid": 2338710, + "ts": 6410534230395.532, "dur": 33116.688, + "args": { + "External id": 1415587,"Record function id": 0, "Ev Idx": 18407 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338710, "tid": 2338710, + "ts": 6410534230403.642, "dur": 942.270, + "args": { + "External id": 1415588,"Record function id": 0, "Ev Idx": 18408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534230507.438, "dur": 9.618, + "args": { + "External id": 1415589,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534230530.694, "dur": 36.448, + "args": { + "External id": 1415590,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230536.663, "dur": 2.254, + "args": { + "External id": 1415591,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230542.467, "dur": 0.440, + "args": { + "External id": 1415592,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230544.146, "dur": 0.692, + "args": { + "External id": 1415593,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230546.317, "dur": 0.446, + "args": { + "External id": 1415594,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230549.350, "dur": 0.515, + "args": { + "External id": 1415595,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230551.761, "dur": 0.402, + "args": { + "External id": 1415596,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230553.419, "dur": 3.556, + "args": { + "External id": 1415597,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230558.471, "dur": 0.287, + "args": { + "External id": 1415598,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230560.803, "dur": 0.340, + "args": { + "External id": 1415599,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534230579.365, "dur": 57.702, + "args": { + "External id": 1415600,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410534230671.612, "dur": 122.588, + "args": { + "External id": 1415601,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534230682.985, "dur": 4.651, + "args": { + "External id": 1415602,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410534230692.744, "dur": 10.552, + "args": { + "External id": 1415603,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534230697.423, "dur": 5.433, + "args": { + "External id": 1415604,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230701.020, "dur": 0.612, + "args": { + "External id": 1415605,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534230710.193, "dur": 28.840, + "args": { + "External id": 1415606,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230712.438, "dur": 1.638, + "args": { + "External id": 1415607,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230715.485, "dur": 0.598, + "args": { + "External id": 1415608,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230717.416, "dur": 0.509, + "args": { + "External id": 1415609,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230720.903, "dur": 2.436, + "args": { + "External id": 1415610,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230724.645, "dur": 0.374, + "args": { + "External id": 1415611,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230726.463, "dur": 0.344, + "args": { + "External id": 1415612,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230729.762, "dur": 0.376, + "args": { + "External id": 1415613,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230731.583, "dur": 0.374, + "args": { + "External id": 1415614,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534230733.615, "dur": 1.334, + "args": { + "External id": 1415615,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534230753.006, "dur": 33.446, + "args": { + "External id": 1415616,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410534230846.572, "dur": 395.907, + "args": { + "External id": 1415617,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534230878.853, "dur": 357.883, + "args": { + "External id": 1415618,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18438, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410534230890.142, "dur": 339.763, + "args": { + "External id": 1415619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534231270.402, "dur": 2.531, + "args": { + "External id": 1415620,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 18440, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338710, "tid": 2338710, + "ts": 6410534231366.508, "dur": 31899.770, + "args": { + "External id": 1415621,"Record function id": 0, "Ev Idx": 18441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231488.809, "dur": 7.074, + "args": { + "External id": 1415622,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231499.394, "dur": 1.140, + "args": { + "External id": 1415623,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231502.280, "dur": 3.096, + "args": { + "External id": 1415624,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231507.092, "dur": 1.124, + "args": { + "External id": 1415625,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231509.330, "dur": 1.005, + "args": { + "External id": 1415626,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231511.612, "dur": 1.194, + "args": { + "External id": 1415627,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231514.332, "dur": 1.006, + "args": { + "External id": 1415628,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231517.389, "dur": 1.900, + "args": { + "External id": 1415629,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231520.687, "dur": 1.020, + "args": { + "External id": 1415630,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534231525.332, "dur": 0.857, + "args": { + "External id": 1415631,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534231544.149, "dur": 31658.977, + "args": { + "External id": 1415632,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534231559.673, "dur": 31630.836, + "args": { + "External id": 1415633,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534231576.023, "dur": 16.325, + "args": { + "External id": 1415634,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534231595.854, "dur": 31546.577, + "args": { + "External id": 1415635,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534231598.716, "dur": 31542.499, + "args": { + "External id": 1415636,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534231605.014, "dur": 5.820, + "args": { + "External id": 1415637,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534231612.585, "dur": 31522.888, + "args": { + "External id": 1415638,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534263443.656, "dur": 37.927, + "args": { + "External id": 1415639,"Sequence number": 15109120, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18459 + } + }, + { + "ph": "s", "id": 399, "pid": 2338710, "tid": 2338710, "ts": 6410534263443.656, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534263464.226, "dur": 12.280, + "args": { + "External id": 1415640,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534263469.112, "dur": 6.948, + "args": { + "External id": 1415641,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534263554.326, "dur": 69.137, + "args": { + "External id": 1415642,"Record function id": 0, "Ev Idx": 18462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534263625.280, "dur": 1139.466, + "args": { + "External id": 1415643,"Record function id": 0, "Ev Idx": 18463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534263664.148, "dur": 1086.830, + "args": { + "External id": 1415644,"Sequence number": 15109121, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18464 + } + }, + { + "ph": "s", "id": 398, "pid": 2338710, "tid": 2338710, "ts": 6410534263664.148, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534263733.320, "dur": 54.059, + "args": { + "External id": 1415645,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534263800.391, "dur": 102.986, + "args": { + "External id": 1415646,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534263916.569, "dur": 43.448, + "args": { + "External id": 1415647,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534263968.331, "dur": 30.289, + "args": { + "External id": 1415648,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534264025.851, "dur": 69.043, + "args": { + "External id": 1415649,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534264121.151, "dur": 19.908, + "args": { + "External id": 1415650,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534264163.355, "dur": 130.924, + "args": { + "External id": 1415651,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534264215.113, "dur": 11.971, + "args": { + "External id": 1415652,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534264220.834, "dur": 5.279, + "args": { + "External id": 1415653,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534264229.642, "dur": 4.440, + "args": { + "External id": 1415654,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534264235.424, "dur": 0.956, + "args": { + "External id": 1415655,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534264238.748, "dur": 5.596, + "args": { + "External id": 1415656,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534264304.806, "dur": 54.312, + "args": { + "External id": 1415657,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534264391.743, "dur": 45.021, + "args": { + "External id": 1415658,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534264449.826, "dur": 47.325, + "args": { + "External id": 1415659,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534264510.131, "dur": 36.446, + "args": { + "External id": 1415660,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534264573.255, "dur": 28.834, + "args": { + "External id": 1415661,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534264609.758, "dur": 37.463, + "args": { + "External id": 1415662,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534264665.840, "dur": 18.652, + "args": { + "External id": 1415663,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18483 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.24)", "pid": 2338710, "tid": 2338710, + "ts": 6410534264830.562, "dur": 79.025, + "args": { + "External id": 1415664,"Record function id": 0, "Ev Idx": 18484 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338710, "tid": 2338710, + "ts": 6410534264982.719, "dur": 46.894, + "args": { + "External id": 1415665,"Record function id": 0, "Ev Idx": 18485 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 2338710, "tid": 2338710, + "ts": 6410534265038.253, "dur": 31167.950, + "args": { + "External id": 1415666,"Record function id": 0, "Ev Idx": 18486 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 2338710, "tid": 2338710, + "ts": 6410534265046.485, "dur": 1044.610, + "args": { + "External id": 1415667,"Record function id": 0, "Ev Idx": 18487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534265175.147, "dur": 10.226, + "args": { + "External id": 1415668,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534265199.690, "dur": 37.901, + "args": { + "External id": 1415669,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265205.459, "dur": 2.201, + "args": { + "External id": 1415670,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265212.090, "dur": 0.490, + "args": { + "External id": 1415671,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265214.682, "dur": 0.393, + "args": { + "External id": 1415672,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265216.616, "dur": 0.511, + "args": { + "External id": 1415673,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265220.243, "dur": 0.409, + "args": { + "External id": 1415674,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265221.693, "dur": 0.404, + "args": { + "External id": 1415675,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265223.584, "dur": 3.964, + "args": { + "External id": 1415676,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265228.726, "dur": 0.367, + "args": { + "External id": 1415677,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265231.074, "dur": 0.346, + "args": { + "External id": 1415678,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534265250.393, "dur": 54.673, + "args": { + "External id": 1415679,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338710, "tid": 2338710, + "ts": 6410534265338.443, "dur": 165.443, + "args": { + "External id": 1415680,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "4", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534265366.128, "dur": 5.101, + "args": { + "External id": 1415681,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338710, "tid": 2338710, + "ts": 6410534265376.572, "dur": 10.550, + "args": { + "External id": 1415682,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534265380.980, "dur": 5.756, + "args": { + "External id": 1415683,"Record function id": 0, "Concrete Inputs": ["", "0", "109056000", "136320000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265384.713, "dur": 0.700, + "args": { + "External id": 1415684,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338710, "tid": 2338710, + "ts": 6410534265394.506, "dur": 46.799, + "args": { + "External id": 1415685,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265401.691, "dur": 0.376, + "args": { + "External id": 1415686,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "109056000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265405.173, "dur": 0.429, + "args": { + "External id": 1415687,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "109056512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265406.611, "dur": 0.329, + "args": { + "External id": 1415688,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111153664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265408.398, "dur": 3.972, + "args": { + "External id": 1415689,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "111677952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265413.566, "dur": 0.274, + "args": { + "External id": 1415690,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "112202240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265430.333, "dur": 0.490, + "args": { + "External id": 1415691,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "114299392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265433.671, "dur": 0.342, + "args": { + "External id": 1415692,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "114299904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265435.333, "dur": 0.174, + "args": { + "External id": 1415693,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "121639936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534265436.521, "dur": 0.326, + "args": { + "External id": 1415694,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "128979968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534265457.380, "dur": 38.216, + "args": { + "External id": 1415695,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338710, "tid": 2338710, + "ts": 6410534265560.893, "dur": 397.787, + "args": { + "External id": 1415696,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534265590.924, "dur": 362.729, + "args": { + "External id": 1415697,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 4, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18517, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338710, "tid": 2338710, + "ts": 6410534265601.495, "dur": 344.400, + "args": { + "External id": 1415698,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410534265983.390, "dur": 2.315, + "args": { + "External id": 1415699,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 18519, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 2338710, "tid": 2338710, + "ts": 6410534266117.174, "dur": 29834.079, + "args": { + "External id": 1415700,"Record function id": 0, "Ev Idx": 18520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266227.763, "dur": 7.339, + "args": { + "External id": 1415701,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266238.299, "dur": 1.102, + "args": { + "External id": 1415702,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266240.992, "dur": 3.395, + "args": { + "External id": 1415703,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266246.052, "dur": 0.723, + "args": { + "External id": 1415704,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266247.965, "dur": 0.782, + "args": { + "External id": 1415705,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266249.973, "dur": 0.593, + "args": { + "External id": 1415706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266251.979, "dur": 0.783, + "args": { + "External id": 1415707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266254.236, "dur": 2.226, + "args": { + "External id": 1415708,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266257.698, "dur": 0.830, + "args": { + "External id": 1415709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534266262.032, "dur": 0.772, + "args": { + "External id": 1415710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534266279.906, "dur": 29612.099, + "args": { + "External id": 1415711,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534266295.348, "dur": 29584.998, + "args": { + "External id": 1415712,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534266315.477, "dur": 16.154, + "args": { + "External id": 1415713,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534266335.259, "dur": 29502.033, + "args": { + "External id": 1415714,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534266337.613, "dur": 29498.460, + "args": { + "External id": 1415715,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534266343.342, "dur": 5.951, + "args": { + "External id": 1415716,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534266351.125, "dur": 29480.148, + "args": { + "External id": 1415717,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534296139.679, "dur": 35.999, + "args": { + "External id": 1415718,"Sequence number": 15109122, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18538 + } + }, + { + "ph": "s", "id": 397, "pid": 2338710, "tid": 2338710, "ts": 6410534296139.679, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534296158.928, "dur": 11.782, + "args": { + "External id": 1415719,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534296163.557, "dur": 6.756, + "args": { + "External id": 1415720,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534296248.028, "dur": 71.075, + "args": { + "External id": 1415721,"Record function id": 0, "Ev Idx": 18541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338710, "tid": 2338710, + "ts": 6410534296320.347, "dur": 1161.735, + "args": { + "External id": 1415722,"Record function id": 0, "Ev Idx": 18542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534296358.687, "dur": 1108.357, + "args": { + "External id": 1415723,"Sequence number": 15109123, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18543 + } + }, + { + "ph": "s", "id": 396, "pid": 2338710, "tid": 2338710, "ts": 6410534296358.687, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534296443.326, "dur": 55.555, + "args": { + "External id": 1415724,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534296513.652, "dur": 105.656, + "args": { + "External id": 1415725,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534296631.468, "dur": 41.122, + "args": { + "External id": 1415726,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534296681.243, "dur": 29.894, + "args": { + "External id": 1415727,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534296739.577, "dur": 26.640, + "args": { + "External id": 1415728,"kernel_hash": "cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/d5/cd5ftgdvg3zpepgpcumeff4mou3c2fy27oihfnqypjiirszq7kos.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338710, "tid": 2338710, + "ts": 6410534296785.697, "dur": 18.390, + "args": { + "External id": 1415729,"kernel_hash": "cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/yr/cyroqezuoeuamd3jqkugypuyres5u7ufws5x3bgos5atsczyhyk3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534296825.620, "dur": 131.320, + "args": { + "External id": 1415730,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534296874.364, "dur": 13.600, + "args": { + "External id": 1415731,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534296879.812, "dur": 7.261, + "args": { + "External id": 1415732,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534296890.707, "dur": 4.208, + "args": { + "External id": 1415733,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534296896.014, "dur": 1.066, + "args": { + "External id": 1415734,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534296899.384, "dur": 4.848, + "args": { + "External id": 1415735,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534296967.554, "dur": 47.982, + "args": { + "External id": 1415736,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338710, "tid": 2338710, + "ts": 6410534297046.829, "dur": 85.228, + "args": { + "External id": 1415737,"kernel_hash": "c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/5x/c5xfababnpqt3wuhdecdmhwvhcvmdznprunosm6exvj2vpztzphf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534297147.775, "dur": 50.884, + "args": { + "External id": 1415738,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534297207.642, "dur": 36.276, + "args": { + "External id": 1415739,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534297272.944, "dur": 29.680, + "args": { + "External id": 1415740,"kernel_hash": "cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uy/cuyinmnu22ra2lhbf5b3kn2pvmpzmlkeucl5ymtesvmjkft4vxxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534297309.667, "dur": 36.956, + "args": { + "External id": 1415741,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338710, "tid": 2338710, + "ts": 6410534297366.313, "dur": 18.709, + "args": { + "External id": 1415742,"kernel_hash": "cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqo6qtnieavgrnue4llkfxac3bydsk5p7r22potmkpxvtg3jxrsu.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18562 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.25)", "pid": 2338710, "tid": 2338710, + "ts": 6410534297551.906, "dur": 34.269, + "args": { + "External id": 1415743,"Record function id": 0, "Ev Idx": 18563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534297721.203, "dur": 284.103, + "args": { + "External id": 1415744,"Sequence number": 15109124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 18564 + } + }, + { + "ph": "s", "id": 395, "pid": 2338710, "tid": 2338710, "ts": 6410534297721.203, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534297753.758, "dur": 8.238, + "args": { + "External id": 1415745,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534297755.754, "dur": 5.967, + "args": { + "External id": 1415746,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534297771.730, "dur": 13.502, + "args": { + "External id": 1415747,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534297775.550, "dur": 9.078, + "args": { + "External id": 1415748,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534297795.764, "dur": 5.800, + "args": { + "External id": 1415749,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534297988.390, "dur": 5.279, + "args": { + "External id": 1415750,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534297990.950, "dur": 2.484, + "args": { + "External id": 1415751,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534298033.442, "dur": 188.016, + "args": { + "External id": 1415752,"Sequence number": 15109125, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534298035.927, "dur": 51.656, + "args": { + "External id": 1415753,"Sequence number": 15109125, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18573 + } + }, + { + "ph": "s", "id": 394, "pid": 2338710, "tid": 2338710, "ts": 6410534298035.927, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534298041.664, "dur": 8.955, + "args": { + "External id": 1415754,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534298048.130, "dur": 2.074, + "args": { + "External id": 1415755,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534298090.635, "dur": 130.311, + "args": { + "External id": 1415756,"Sequence number": 15109126, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534298094.890, "dur": 6.356, + "args": { + "External id": 1415757,"Sequence number": 15109126, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298095.817, "dur": 5.304, + "args": { + "External id": 1415758,"Sequence number": 15109126, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18578 + } + }, + { + "ph": "s", "id": 393, "pid": 2338710, "tid": 2338710, "ts": 6410534298095.817, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534298105.363, "dur": 103.749, + "args": { + "External id": 1415759,"Sequence number": 15109127, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18579 + } + }, + { + "ph": "s", "id": 392, "pid": 2338710, "tid": 2338710, "ts": 6410534298105.363, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298212.664, "dur": 7.168, + "args": { + "External id": 1415760,"Sequence number": 15109128, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18580 + } + }, + { + "ph": "s", "id": 391, "pid": 2338710, "tid": 2338710, "ts": 6410534298212.664, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534298234.582, "dur": 72.893, + "args": { + "External id": 1415761,"Sequence number": 15109129, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534298235.616, "dur": 8.882, + "args": { + "External id": 1415762,"Sequence number": 15109129, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18582 + } + }, + { + "ph": "s", "id": 390, "pid": 2338710, "tid": 2338710, "ts": 6410534298235.616, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534298237.782, "dur": 5.511, + "args": { + "External id": 1415763,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534298241.716, "dur": 1.377, + "args": { + "External id": 1415764,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534298245.411, "dur": 61.754, + "args": { + "External id": 1415765,"Sequence number": 15109130, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534298246.746, "dur": 4.605, + "args": { + "External id": 1415766,"Sequence number": 15109130, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298247.597, "dur": 3.599, + "args": { + "External id": 1415767,"Sequence number": 15109130, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18587 + } + }, + { + "ph": "s", "id": 389, "pid": 2338710, "tid": 2338710, "ts": 6410534298247.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534298252.024, "dur": 47.564, + "args": { + "External id": 1415768,"Sequence number": 15109131, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18588 + } + }, + { + "ph": "s", "id": 388, "pid": 2338710, "tid": 2338710, "ts": 6410534298252.024, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298302.032, "dur": 4.763, + "args": { + "External id": 1415769,"Sequence number": 15109132, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18589 + } + }, + { + "ph": "s", "id": 387, "pid": 2338710, "tid": 2338710, "ts": 6410534298302.032, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534298315.897, "dur": 65.188, + "args": { + "External id": 1415770,"Sequence number": 15109133, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534298316.533, "dur": 5.929, + "args": { + "External id": 1415771,"Sequence number": 15109133, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18591 + } + }, + { + "ph": "s", "id": 386, "pid": 2338710, "tid": 2338710, "ts": 6410534298316.533, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534298318.426, "dur": 2.929, + "args": { + "External id": 1415772,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534298320.151, "dur": 1.076, + "args": { + "External id": 1415773,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534298325.229, "dur": 55.649, + "args": { + "External id": 1415774,"Sequence number": 15109134, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534298326.568, "dur": 4.672, + "args": { + "External id": 1415775,"Sequence number": 15109134, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298327.221, "dur": 3.889, + "args": { + "External id": 1415776,"Sequence number": 15109134, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18596 + } + }, + { + "ph": "s", "id": 385, "pid": 2338710, "tid": 2338710, "ts": 6410534298327.221, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534298331.691, "dur": 40.960, + "args": { + "External id": 1415777,"Sequence number": 15109135, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18597 + } + }, + { + "ph": "s", "id": 384, "pid": 2338710, "tid": 2338710, "ts": 6410534298331.691, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298374.546, "dur": 5.956, + "args": { + "External id": 1415778,"Sequence number": 15109136, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18598 + } + }, + { + "ph": "s", "id": 383, "pid": 2338710, "tid": 2338710, "ts": 6410534298374.546, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534298403.615, "dur": 4.545, + "args": { + "External id": 1415779,"Sequence number": 15109137, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298404.807, "dur": 3.232, + "args": { + "External id": 1415780,"Sequence number": 15109137, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18600 + } + }, + { + "ph": "s", "id": 382, "pid": 2338710, "tid": 2338710, "ts": 6410534298404.807, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534298431.214, "dur": 5.187, + "args": { + "External id": 1415781,"Sequence number": 15109138, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298432.718, "dur": 3.433, + "args": { + "External id": 1415782,"Sequence number": 15109138, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18602 + } + }, + { + "ph": "s", "id": 381, "pid": 2338710, "tid": 2338710, "ts": 6410534298432.718, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534298445.099, "dur": 4.886, + "args": { + "External id": 1415783,"Sequence number": 15109139, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534298446.157, "dur": 3.681, + "args": { + "External id": 1415784,"Sequence number": 15109139, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18604 + } + }, + { + "ph": "s", "id": 380, "pid": 2338710, "tid": 2338710, "ts": 6410534298446.157, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534298488.333, "dur": 192.538, + "args": { + "External id": 1415785,"Sequence number": 15109140, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18605 + } + }, + { + "ph": "s", "id": 379, "pid": 2338710, "tid": 2338710, "ts": 6410534298488.333, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534298510.990, "dur": 10.868, + "args": { + "External id": 1415786,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534298514.901, "dur": 6.505, + "args": { + "External id": 1415787,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534298694.227, "dur": 114.008, + "args": { + "External id": 1415788,"Sequence number": 15109141, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18608 + } + }, + { + "ph": "s", "id": 378, "pid": 2338710, "tid": 2338710, "ts": 6410534298694.227, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534298709.159, "dur": 8.352, + "args": { + "External id": 1415789,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 18609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534298711.931, "dur": 5.170, + "args": { + "External id": 1415790,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338710, "tid": 2338710, + "ts": 6410534298838.302, "dur": 191.496, + "args": { + "External id": 1415791,"Sequence number": 15109142, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 18611 + } + }, + { + "ph": "s", "id": 377, "pid": 2338710, "tid": 2338710, "ts": 6410534298838.302, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534298869.618, "dur": 132.042, + "args": { + "External id": 1415792,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534298923.878, "dur": 9.074, + "args": { + "External id": 1415793,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534298926.616, "dur": 5.774, + "args": { + "External id": 1415794,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534298935.890, "dur": 3.968, + "args": { + "External id": 1415795,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534298940.868, "dur": 1.090, + "args": { + "External id": 1415796,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534298944.352, "dur": 3.730, + "args": { + "External id": 1415797,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410534299016.326, "dur": 5.189, + "args": { + "External id": 1415798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 18618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299035.442, "dur": 6.644, + "args": { + "External id": 1415799,"Sequence number": 15109143, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299036.952, "dur": 4.973, + "args": { + "External id": 1415800,"Sequence number": 15109143, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18620 + } + }, + { + "ph": "s", "id": 376, "pid": 2338710, "tid": 2338710, "ts": 6410534299036.952, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534299091.664, "dur": 125.865, + "args": { + "External id": 1415801,"Sequence number": 15109144, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534299094.787, "dur": 10.339, + "args": { + "External id": 1415802,"Sequence number": 15109144, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18622 + } + }, + { + "ph": "s", "id": 375, "pid": 2338710, "tid": 2338710, "ts": 6410534299094.787, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534299098.038, "dur": 5.342, + "args": { + "External id": 1415803,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534299100.688, "dur": 2.054, + "args": { + "External id": 1415804,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534299106.527, "dur": 110.694, + "args": { + "External id": 1415805,"Sequence number": 15109145, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299108.446, "dur": 7.267, + "args": { + "External id": 1415806,"Sequence number": 15109145, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299111.625, "dur": 3.959, + "args": { + "External id": 1415807,"Sequence number": 15109145, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18627 + } + }, + { + "ph": "s", "id": 374, "pid": 2338710, "tid": 2338710, "ts": 6410534299111.625, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534299116.755, "dur": 93.052, + "args": { + "External id": 1415808,"Sequence number": 15109146, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18628 + } + }, + { + "ph": "s", "id": 373, "pid": 2338710, "tid": 2338710, "ts": 6410534299116.755, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299212.591, "dur": 3.855, + "args": { + "External id": 1415809,"Sequence number": 15109147, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18629 + } + }, + { + "ph": "s", "id": 372, "pid": 2338710, "tid": 2338710, "ts": 6410534299212.591, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534299257.911, "dur": 260.133, + "args": { + "External id": 1415810,"Sequence number": 15109148, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 18630 + } + }, + { + "ph": "s", "id": 371, "pid": 2338710, "tid": 2338710, "ts": 6410534299257.911, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299282.186, "dur": 3.620, + "args": { + "External id": 1415811,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299282.851, "dur": 2.795, + "args": { + "External id": 1415812,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534299290.518, "dur": 4.889, + "args": { + "External id": 1415813,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 18633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299291.391, "dur": 3.890, + "args": { + "External id": 1415814,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299292.642, "dur": 2.513, + "args": { + "External id": 1415815,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534299303.494, "dur": 10.166, + "args": { + "External id": 1415816,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534299308.359, "dur": 4.994, + "args": { + "External id": 1415817,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534299320.329, "dur": 3.337, + "args": { + "External id": 1415818,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534299327.160, "dur": 3.068, + "args": { + "External id": 1415819,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299490.068, "dur": 4.690, + "args": { + "External id": 1415820,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299491.467, "dur": 2.915, + "args": { + "External id": 1415821,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299497.867, "dur": 4.879, + "args": { + "External id": 1415822,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299501.458, "dur": 1.182, + "args": { + "External id": 1415823,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534299539.227, "dur": 107.918, + "args": { + "External id": 1415824,"Sequence number": 15109149, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534299540.479, "dur": 8.331, + "args": { + "External id": 1415825,"Sequence number": 15109149, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18645 + } + }, + { + "ph": "s", "id": 370, "pid": 2338710, "tid": 2338710, "ts": 6410534299540.479, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534299543.018, "dur": 4.595, + "args": { + "External id": 1415826,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534299545.400, "dur": 1.953, + "args": { + "External id": 1415827,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534299549.912, "dur": 96.845, + "args": { + "External id": 1415828,"Sequence number": 15109150, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299553.946, "dur": 3.783, + "args": { + "External id": 1415829,"Sequence number": 15109150, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299554.532, "dur": 3.028, + "args": { + "External id": 1415830,"Sequence number": 15109150, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18650 + } + }, + { + "ph": "s", "id": 369, "pid": 2338710, "tid": 2338710, "ts": 6410534299554.532, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534299558.502, "dur": 79.379, + "args": { + "External id": 1415831,"Sequence number": 15109151, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18651 + } + }, + { + "ph": "s", "id": 368, "pid": 2338710, "tid": 2338710, "ts": 6410534299558.502, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299640.293, "dur": 5.847, + "args": { + "External id": 1415832,"Sequence number": 15109152, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18652 + } + }, + { + "ph": "s", "id": 367, "pid": 2338710, "tid": 2338710, "ts": 6410534299640.293, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534299658.915, "dur": 71.077, + "args": { + "External id": 1415833,"Sequence number": 15109153, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534299659.449, "dur": 6.405, + "args": { + "External id": 1415834,"Sequence number": 15109153, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18654 + } + }, + { + "ph": "s", "id": 366, "pid": 2338710, "tid": 2338710, "ts": 6410534299659.449, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534299661.647, "dur": 2.953, + "args": { + "External id": 1415835,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534299663.623, "dur": 0.846, + "args": { + "External id": 1415836,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534299666.820, "dur": 62.841, + "args": { + "External id": 1415837,"Sequence number": 15109154, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299669.861, "dur": 5.412, + "args": { + "External id": 1415838,"Sequence number": 15109154, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299670.905, "dur": 4.254, + "args": { + "External id": 1415839,"Sequence number": 15109154, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18659 + } + }, + { + "ph": "s", "id": 365, "pid": 2338710, "tid": 2338710, "ts": 6410534299670.905, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534299675.977, "dur": 49.088, + "args": { + "External id": 1415840,"Sequence number": 15109155, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18660 + } + }, + { + "ph": "s", "id": 364, "pid": 2338710, "tid": 2338710, "ts": 6410534299675.977, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299727.062, "dur": 2.216, + "args": { + "External id": 1415841,"Sequence number": 15109156, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18661 + } + }, + { + "ph": "s", "id": 363, "pid": 2338710, "tid": 2338710, "ts": 6410534299727.062, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534299754.735, "dur": 170.153, + "args": { + "External id": 1415842,"Sequence number": 15109157, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18662 + } + }, + { + "ph": "s", "id": 362, "pid": 2338710, "tid": 2338710, "ts": 6410534299754.735, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534299800.114, "dur": 4.869, + "args": { + "External id": 1415843,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534299843.251, "dur": 68.303, + "args": { + "External id": 1415844,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534299844.122, "dur": 6.539, + "args": { + "External id": 1415845,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 18665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534299846.527, "dur": 3.215, + "args": { + "External id": 1415846,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 18666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534299848.749, "dur": 0.792, + "args": { + "External id": 1415847,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 18667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534299851.475, "dur": 59.675, + "args": { + "External id": 1415848,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 18668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534299855.397, "dur": 2.192, + "args": { + "External id": 1415849,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299856.294, "dur": 1.160, + "args": { + "External id": 1415850,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534299858.027, "dur": 49.122, + "args": { + "External id": 1415851,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 18671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534299909.336, "dur": 1.159, + "args": { + "External id": 1415852,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410534299935.761, "dur": 29.926, + "args": { + "External id": 1415853,"Sequence number": 15109158, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 18673 + } + }, + { + "ph": "s", "id": 361, "pid": 2338710, "tid": 2338710, "ts": 6410534299935.761, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534300000.985, "dur": 237.944, + "args": { + "External id": 1415854,"Sequence number": 15109159, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 18674 + } + }, + { + "ph": "s", "id": 360, "pid": 2338710, "tid": 2338710, "ts": 6410534300000.985, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534300020.880, "dur": 3.570, + "args": { + "External id": 1415855,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300022.057, "dur": 2.208, + "args": { + "External id": 1415856,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534300031.877, "dur": 7.393, + "args": { + "External id": 1415857,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534300034.717, "dur": 4.077, + "args": { + "External id": 1415858,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534300045.349, "dur": 3.104, + "args": { + "External id": 1415859,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534300220.967, "dur": 4.628, + "args": { + "External id": 1415860,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300222.168, "dur": 3.097, + "args": { + "External id": 1415861,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534300259.486, "dur": 104.761, + "args": { + "External id": 1415862,"Sequence number": 15109160, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534300263.221, "dur": 8.460, + "args": { + "External id": 1415863,"Sequence number": 15109160, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18683 + } + }, + { + "ph": "s", "id": 359, "pid": 2338710, "tid": 2338710, "ts": 6410534300263.221, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534300266.094, "dur": 4.081, + "args": { + "External id": 1415864,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534300268.071, "dur": 1.816, + "args": { + "External id": 1415865,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534300272.861, "dur": 91.074, + "args": { + "External id": 1415866,"Sequence number": 15109161, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534300274.218, "dur": 8.602, + "args": { + "External id": 1415867,"Sequence number": 15109161, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300277.121, "dur": 5.559, + "args": { + "External id": 1415868,"Sequence number": 15109161, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18688 + } + }, + { + "ph": "s", "id": 358, "pid": 2338710, "tid": 2338710, "ts": 6410534300277.121, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534300283.683, "dur": 72.490, + "args": { + "External id": 1415869,"Sequence number": 15109162, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18689 + } + }, + { + "ph": "s", "id": 357, "pid": 2338710, "tid": 2338710, "ts": 6410534300283.683, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300358.667, "dur": 4.475, + "args": { + "External id": 1415870,"Sequence number": 15109163, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18690 + } + }, + { + "ph": "s", "id": 356, "pid": 2338710, "tid": 2338710, "ts": 6410534300358.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534300373.106, "dur": 90.072, + "args": { + "External id": 1415871,"Sequence number": 15109164, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534300373.685, "dur": 9.083, + "args": { + "External id": 1415872,"Sequence number": 15109164, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18692 + } + }, + { + "ph": "s", "id": 355, "pid": 2338710, "tid": 2338710, "ts": 6410534300373.685, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534300378.971, "dur": 2.324, + "args": { + "External id": 1415873,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534300380.388, "dur": 0.747, + "args": { + "External id": 1415874,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534300383.403, "dur": 79.525, + "args": { + "External id": 1415875,"Sequence number": 15109165, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534300384.717, "dur": 5.887, + "args": { + "External id": 1415876,"Sequence number": 15109165, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300387.639, "dur": 2.800, + "args": { + "External id": 1415877,"Sequence number": 15109165, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18697 + } + }, + { + "ph": "s", "id": 354, "pid": 2338710, "tid": 2338710, "ts": 6410534300387.639, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534300391.179, "dur": 63.770, + "args": { + "External id": 1415878,"Sequence number": 15109166, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18698 + } + }, + { + "ph": "s", "id": 353, "pid": 2338710, "tid": 2338710, "ts": 6410534300391.179, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300457.948, "dur": 4.030, + "args": { + "External id": 1415879,"Sequence number": 15109167, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18699 + } + }, + { + "ph": "s", "id": 352, "pid": 2338710, "tid": 2338710, "ts": 6410534300457.948, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534300471.835, "dur": 66.992, + "args": { + "External id": 1415880,"Sequence number": 15109168, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534300472.645, "dur": 7.970, + "args": { + "External id": 1415881,"Sequence number": 15109168, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18701 + } + }, + { + "ph": "s", "id": 351, "pid": 2338710, "tid": 2338710, "ts": 6410534300472.645, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534300474.194, "dur": 5.277, + "args": { + "External id": 1415882,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534300478.675, "dur": 0.658, + "args": { + "External id": 1415883,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534300481.200, "dur": 57.402, + "args": { + "External id": 1415884,"Sequence number": 15109169, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534300482.305, "dur": 7.463, + "args": { + "External id": 1415885,"Sequence number": 15109169, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300483.369, "dur": 6.259, + "args": { + "External id": 1415886,"Sequence number": 15109169, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18706 + } + }, + { + "ph": "s", "id": 350, "pid": 2338710, "tid": 2338710, "ts": 6410534300483.369, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534300492.547, "dur": 40.962, + "args": { + "External id": 1415887,"Sequence number": 15109170, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18707 + } + }, + { + "ph": "s", "id": 349, "pid": 2338710, "tid": 2338710, "ts": 6410534300492.547, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300535.450, "dur": 2.659, + "args": { + "External id": 1415888,"Sequence number": 15109171, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18708 + } + }, + { + "ph": "s", "id": 348, "pid": 2338710, "tid": 2338710, "ts": 6410534300535.450, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534300555.527, "dur": 5.867, + "args": { + "External id": 1415889,"Sequence number": 15109172, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300556.429, "dur": 4.800, + "args": { + "External id": 1415890,"Sequence number": 15109172, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18710 + } + }, + { + "ph": "s", "id": 347, "pid": 2338710, "tid": 2338710, "ts": 6410534300556.429, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534300568.248, "dur": 5.932, + "args": { + "External id": 1415891,"Sequence number": 15109173, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300571.836, "dur": 2.218, + "args": { + "External id": 1415892,"Sequence number": 15109173, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18712 + } + }, + { + "ph": "s", "id": 346, "pid": 2338710, "tid": 2338710, "ts": 6410534300571.836, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534300578.334, "dur": 3.540, + "args": { + "External id": 1415893,"Sequence number": 15109174, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534300579.614, "dur": 2.146, + "args": { + "External id": 1415894,"Sequence number": 15109174, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18714 + } + }, + { + "ph": "s", "id": 345, "pid": 2338710, "tid": 2338710, "ts": 6410534300579.614, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534300612.805, "dur": 169.947, + "args": { + "External id": 1415895,"Sequence number": 15109175, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18715 + } + }, + { + "ph": "s", "id": 344, "pid": 2338710, "tid": 2338710, "ts": 6410534300612.805, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534300633.454, "dur": 18.132, + "args": { + "External id": 1415896,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534300640.511, "dur": 10.617, + "args": { + "External id": 1415897,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534300798.382, "dur": 108.331, + "args": { + "External id": 1415898,"Sequence number": 15109176, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18718 + } + }, + { + "ph": "s", "id": 343, "pid": 2338710, "tid": 2338710, "ts": 6410534300798.382, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534300811.958, "dur": 8.184, + "args": { + "External id": 1415899,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 18719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534300814.388, "dur": 5.305, + "args": { + "External id": 1415900,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338710, "tid": 2338710, + "ts": 6410534300935.315, "dur": 225.443, + "args": { + "External id": 1415901,"Sequence number": 15109177, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 18721 + } + }, + { + "ph": "s", "id": 342, "pid": 2338710, "tid": 2338710, "ts": 6410534300935.315, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534300966.556, "dur": 165.440, + "args": { + "External id": 1415902,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534301014.863, "dur": 8.031, + "args": { + "External id": 1415903,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534301018.758, "dur": 3.729, + "args": { + "External id": 1415904,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534301025.581, "dur": 4.384, + "args": { + "External id": 1415905,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534301031.160, "dur": 0.947, + "args": { + "External id": 1415906,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534301034.633, "dur": 3.747, + "args": { + "External id": 1415907,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410534301145.610, "dur": 5.094, + "args": { + "External id": 1415908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 18728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301166.742, "dur": 8.051, + "args": { + "External id": 1415909,"Sequence number": 15109178, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301168.278, "dur": 6.367, + "args": { + "External id": 1415910,"Sequence number": 15109178, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18730 + } + }, + { + "ph": "s", "id": 341, "pid": 2338710, "tid": 2338710, "ts": 6410534301168.278, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534301187.159, "dur": 113.778, + "args": { + "External id": 1415911,"Sequence number": 15109179, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534301188.076, "dur": 8.514, + "args": { + "External id": 1415912,"Sequence number": 15109179, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18732 + } + }, + { + "ph": "s", "id": 340, "pid": 2338710, "tid": 2338710, "ts": 6410534301188.076, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534301190.987, "dur": 4.311, + "args": { + "External id": 1415913,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534301193.283, "dur": 1.747, + "args": { + "External id": 1415914,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534301197.947, "dur": 102.677, + "args": { + "External id": 1415915,"Sequence number": 15109180, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301201.687, "dur": 3.756, + "args": { + "External id": 1415916,"Sequence number": 15109180, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301202.787, "dur": 2.516, + "args": { + "External id": 1415917,"Sequence number": 15109180, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18737 + } + }, + { + "ph": "s", "id": 339, "pid": 2338710, "tid": 2338710, "ts": 6410534301202.787, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534301206.281, "dur": 84.757, + "args": { + "External id": 1415918,"Sequence number": 15109181, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18738 + } + }, + { + "ph": "s", "id": 338, "pid": 2338710, "tid": 2338710, "ts": 6410534301206.281, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301293.800, "dur": 6.045, + "args": { + "External id": 1415919,"Sequence number": 15109182, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18739 + } + }, + { + "ph": "s", "id": 337, "pid": 2338710, "tid": 2338710, "ts": 6410534301293.800, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534301338.443, "dur": 236.989, + "args": { + "External id": 1415920,"Sequence number": 15109183, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 18740 + } + }, + { + "ph": "s", "id": 336, "pid": 2338710, "tid": 2338710, "ts": 6410534301338.443, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301357.121, "dur": 3.906, + "args": { + "External id": 1415921,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301359.400, "dur": 1.455, + "args": { + "External id": 1415922,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534301365.370, "dur": 5.154, + "args": { + "External id": 1415923,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 18743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301366.361, "dur": 4.049, + "args": { + "External id": 1415924,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301369.333, "dur": 0.976, + "args": { + "External id": 1415925,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534301377.874, "dur": 8.127, + "args": { + "External id": 1415926,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534301380.644, "dur": 4.981, + "args": { + "External id": 1415927,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534301392.352, "dur": 3.280, + "args": { + "External id": 1415928,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534301399.154, "dur": 3.442, + "args": { + "External id": 1415929,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301553.764, "dur": 4.789, + "args": { + "External id": 1415930,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301554.920, "dur": 3.247, + "args": { + "External id": 1415931,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301561.264, "dur": 1.957, + "args": { + "External id": 1415932,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301562.119, "dur": 0.998, + "args": { + "External id": 1415933,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534301594.967, "dur": 103.629, + "args": { + "External id": 1415934,"Sequence number": 15109184, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534301596.108, "dur": 9.799, + "args": { + "External id": 1415935,"Sequence number": 15109184, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18755 + } + }, + { + "ph": "s", "id": 335, "pid": 2338710, "tid": 2338710, "ts": 6410534301596.108, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534301598.903, "dur": 5.753, + "args": { + "External id": 1415936,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534301602.901, "dur": 1.479, + "args": { + "External id": 1415937,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534301607.011, "dur": 91.242, + "args": { + "External id": 1415938,"Sequence number": 15109185, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301608.821, "dur": 5.496, + "args": { + "External id": 1415939,"Sequence number": 15109185, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301609.367, "dur": 4.785, + "args": { + "External id": 1415940,"Sequence number": 15109185, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18760 + } + }, + { + "ph": "s", "id": 334, "pid": 2338710, "tid": 2338710, "ts": 6410534301609.367, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534301615.104, "dur": 77.439, + "args": { + "External id": 1415941,"Sequence number": 15109186, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18761 + } + }, + { + "ph": "s", "id": 333, "pid": 2338710, "tid": 2338710, "ts": 6410534301615.104, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301694.944, "dur": 2.699, + "args": { + "External id": 1415942,"Sequence number": 15109187, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18762 + } + }, + { + "ph": "s", "id": 332, "pid": 2338710, "tid": 2338710, "ts": 6410534301694.944, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534301706.655, "dur": 69.045, + "args": { + "External id": 1415943,"Sequence number": 15109188, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534301707.110, "dur": 6.157, + "args": { + "External id": 1415944,"Sequence number": 15109188, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18764 + } + }, + { + "ph": "s", "id": 331, "pid": 2338710, "tid": 2338710, "ts": 6410534301707.110, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534301709.132, "dur": 2.751, + "args": { + "External id": 1415945,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534301711.096, "dur": 0.605, + "args": { + "External id": 1415946,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534301716.309, "dur": 59.167, + "args": { + "External id": 1415947,"Sequence number": 15109189, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301716.961, "dur": 6.746, + "args": { + "External id": 1415948,"Sequence number": 15109189, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301717.918, "dur": 5.633, + "args": { + "External id": 1415949,"Sequence number": 15109189, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18769 + } + }, + { + "ph": "s", "id": 330, "pid": 2338710, "tid": 2338710, "ts": 6410534301717.918, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534301724.379, "dur": 44.882, + "args": { + "External id": 1415950,"Sequence number": 15109190, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18770 + } + }, + { + "ph": "s", "id": 329, "pid": 2338710, "tid": 2338710, "ts": 6410534301724.379, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301771.104, "dur": 4.021, + "args": { + "External id": 1415951,"Sequence number": 15109191, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18771 + } + }, + { + "ph": "s", "id": 328, "pid": 2338710, "tid": 2338710, "ts": 6410534301771.104, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534301796.983, "dur": 150.552, + "args": { + "External id": 1415952,"Sequence number": 15109192, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18772 + } + }, + { + "ph": "s", "id": 327, "pid": 2338710, "tid": 2338710, "ts": 6410534301796.983, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534301834.080, "dur": 4.325, + "args": { + "External id": 1415953,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534301874.658, "dur": 59.873, + "args": { + "External id": 1415954,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534301875.429, "dur": 6.618, + "args": { + "External id": 1415955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 18775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534301876.671, "dur": 4.401, + "args": { + "External id": 1415956,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 18776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534301880.301, "dur": 0.604, + "args": { + "External id": 1415957,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 18777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534301882.843, "dur": 51.371, + "args": { + "External id": 1415958,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 18778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534301883.854, "dur": 2.064, + "args": { + "External id": 1415959,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301884.780, "dur": 1.016, + "args": { + "External id": 1415960,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534301886.496, "dur": 44.487, + "args": { + "External id": 1415961,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 18781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534301932.780, "dur": 0.811, + "args": { + "External id": 1415962,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410534301955.848, "dur": 25.323, + "args": { + "External id": 1415963,"Sequence number": 15109193, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 18783 + } + }, + { + "ph": "s", "id": 326, "pid": 2338710, "tid": 2338710, "ts": 6410534301955.848, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534302017.297, "dur": 230.574, + "args": { + "External id": 1415964,"Sequence number": 15109194, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 18784 + } + }, + { + "ph": "s", "id": 325, "pid": 2338710, "tid": 2338710, "ts": 6410534302017.297, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534302033.877, "dur": 2.791, + "args": { + "External id": 1415965,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302034.779, "dur": 1.678, + "args": { + "External id": 1415966,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534302044.398, "dur": 7.017, + "args": { + "External id": 1415967,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534302047.378, "dur": 3.687, + "args": { + "External id": 1415968,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534302096.179, "dur": 5.273, + "args": { + "External id": 1415969,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534302228.725, "dur": 6.067, + "args": { + "External id": 1415970,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302229.576, "dur": 5.044, + "args": { + "External id": 1415971,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534302267.350, "dur": 91.062, + "args": { + "External id": 1415972,"Sequence number": 15109195, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534302268.241, "dur": 7.954, + "args": { + "External id": 1415973,"Sequence number": 15109195, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18793 + } + }, + { + "ph": "s", "id": 324, "pid": 2338710, "tid": 2338710, "ts": 6410534302268.241, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534302271.005, "dur": 3.602, + "args": { + "External id": 1415974,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534302272.851, "dur": 1.463, + "args": { + "External id": 1415975,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534302277.024, "dur": 81.061, + "args": { + "External id": 1415976,"Sequence number": 15109196, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534302280.912, "dur": 3.982, + "args": { + "External id": 1415977,"Sequence number": 15109196, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302281.704, "dur": 3.061, + "args": { + "External id": 1415978,"Sequence number": 15109196, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18798 + } + }, + { + "ph": "s", "id": 323, "pid": 2338710, "tid": 2338710, "ts": 6410534302281.704, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534302285.632, "dur": 64.871, + "args": { + "External id": 1415979,"Sequence number": 15109197, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18799 + } + }, + { + "ph": "s", "id": 322, "pid": 2338710, "tid": 2338710, "ts": 6410534302285.632, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302353.039, "dur": 4.464, + "args": { + "External id": 1415980,"Sequence number": 15109198, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18800 + } + }, + { + "ph": "s", "id": 321, "pid": 2338710, "tid": 2338710, "ts": 6410534302353.039, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534302373.041, "dur": 78.775, + "args": { + "External id": 1415981,"Sequence number": 15109199, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534302373.676, "dur": 5.291, + "args": { + "External id": 1415982,"Sequence number": 15109199, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18802 + } + }, + { + "ph": "s", "id": 320, "pid": 2338710, "tid": 2338710, "ts": 6410534302373.676, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534302375.285, "dur": 2.370, + "args": { + "External id": 1415983,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534302376.825, "dur": 0.694, + "args": { + "External id": 1415984,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534302379.505, "dur": 72.069, + "args": { + "External id": 1415985,"Sequence number": 15109200, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534302382.215, "dur": 4.735, + "args": { + "External id": 1415986,"Sequence number": 15109200, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302382.972, "dur": 3.844, + "args": { + "External id": 1415987,"Sequence number": 15109200, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18807 + } + }, + { + "ph": "s", "id": 319, "pid": 2338710, "tid": 2338710, "ts": 6410534302382.972, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534302387.472, "dur": 57.071, + "args": { + "External id": 1415988,"Sequence number": 15109201, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18808 + } + }, + { + "ph": "s", "id": 318, "pid": 2338710, "tid": 2338710, "ts": 6410534302387.472, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302447.544, "dur": 3.573, + "args": { + "External id": 1415989,"Sequence number": 15109202, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18809 + } + }, + { + "ph": "s", "id": 317, "pid": 2338710, "tid": 2338710, "ts": 6410534302447.544, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534302461.720, "dur": 72.695, + "args": { + "External id": 1415990,"Sequence number": 15109203, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534302462.127, "dur": 9.627, + "args": { + "External id": 1415991,"Sequence number": 15109203, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18811 + } + }, + { + "ph": "s", "id": 316, "pid": 2338710, "tid": 2338710, "ts": 6410534302462.127, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534302466.446, "dur": 4.050, + "args": { + "External id": 1415992,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534302469.616, "dur": 0.732, + "args": { + "External id": 1415993,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534302472.568, "dur": 61.548, + "args": { + "External id": 1415994,"Sequence number": 15109204, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534302473.422, "dur": 9.376, + "args": { + "External id": 1415995,"Sequence number": 15109204, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302476.368, "dur": 6.306, + "args": { + "External id": 1415996,"Sequence number": 15109204, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18816 + } + }, + { + "ph": "s", "id": 315, "pid": 2338710, "tid": 2338710, "ts": 6410534302476.368, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534302483.496, "dur": 45.526, + "args": { + "External id": 1415997,"Sequence number": 15109205, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18817 + } + }, + { + "ph": "s", "id": 314, "pid": 2338710, "tid": 2338710, "ts": 6410534302483.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302531.032, "dur": 2.807, + "args": { + "External id": 1415998,"Sequence number": 15109206, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18818 + } + }, + { + "ph": "s", "id": 313, "pid": 2338710, "tid": 2338710, "ts": 6410534302531.032, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534302551.352, "dur": 5.808, + "args": { + "External id": 1415999,"Sequence number": 15109207, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302552.463, "dur": 4.580, + "args": { + "External id": 1416000,"Sequence number": 15109207, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18820 + } + }, + { + "ph": "s", "id": 312, "pid": 2338710, "tid": 2338710, "ts": 6410534302552.463, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534302563.672, "dur": 3.289, + "args": { + "External id": 1416001,"Sequence number": 15109208, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302564.626, "dur": 2.220, + "args": { + "External id": 1416002,"Sequence number": 15109208, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18822 + } + }, + { + "ph": "s", "id": 311, "pid": 2338710, "tid": 2338710, "ts": 6410534302564.626, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534302570.978, "dur": 2.943, + "args": { + "External id": 1416003,"Sequence number": 15109209, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534302571.735, "dur": 2.077, + "args": { + "External id": 1416004,"Sequence number": 15109209, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18824 + } + }, + { + "ph": "s", "id": 310, "pid": 2338710, "tid": 2338710, "ts": 6410534302571.735, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534302604.979, "dur": 148.650, + "args": { + "External id": 1416005,"Sequence number": 15109210, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18825 + } + }, + { + "ph": "s", "id": 309, "pid": 2338710, "tid": 2338710, "ts": 6410534302604.979, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534302624.476, "dur": 8.856, + "args": { + "External id": 1416006,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534302626.773, "dur": 6.045, + "args": { + "External id": 1416007,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534302765.367, "dur": 102.783, + "args": { + "External id": 1416008,"Sequence number": 15109211, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18828 + } + }, + { + "ph": "s", "id": 308, "pid": 2338710, "tid": 2338710, "ts": 6410534302765.367, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534302777.781, "dur": 6.979, + "args": { + "External id": 1416009,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 18829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534302780.103, "dur": 4.331, + "args": { + "External id": 1416010,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338710, "tid": 2338710, + "ts": 6410534302896.876, "dur": 217.876, + "args": { + "External id": 1416011,"Sequence number": 15109212, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 18831 + } + }, + { + "ph": "s", "id": 307, "pid": 2338710, "tid": 2338710, "ts": 6410534302896.876, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534302922.705, "dur": 125.138, + "args": { + "External id": 1416012,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534302972.299, "dur": 7.114, + "args": { + "External id": 1416013,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534302975.062, "dur": 3.698, + "args": { + "External id": 1416014,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534302981.880, "dur": 4.079, + "args": { + "External id": 1416015,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534302987.530, "dur": 0.855, + "args": { + "External id": 1416016,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534302990.683, "dur": 4.323, + "args": { + "External id": 1416017,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410534303097.027, "dur": 5.196, + "args": { + "External id": 1416018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 18838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303121.641, "dur": 6.706, + "args": { + "External id": 1416019,"Sequence number": 15109213, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303123.381, "dur": 4.834, + "args": { + "External id": 1416020,"Sequence number": 15109213, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18840 + } + }, + { + "ph": "s", "id": 306, "pid": 2338710, "tid": 2338710, "ts": 6410534303123.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534303141.183, "dur": 121.377, + "args": { + "External id": 1416021,"Sequence number": 15109214, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534303142.893, "dur": 12.440, + "args": { + "External id": 1416022,"Sequence number": 15109214, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18842 + } + }, + { + "ph": "s", "id": 305, "pid": 2338710, "tid": 2338710, "ts": 6410534303142.893, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534303147.868, "dur": 6.404, + "args": { + "External id": 1416023,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534303152.287, "dur": 1.723, + "args": { + "External id": 1416024,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534303156.755, "dur": 105.428, + "args": { + "External id": 1416025,"Sequence number": 15109215, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303158.760, "dur": 4.314, + "args": { + "External id": 1416026,"Sequence number": 15109215, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303159.959, "dur": 2.984, + "args": { + "External id": 1416027,"Sequence number": 15109215, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18847 + } + }, + { + "ph": "s", "id": 304, "pid": 2338710, "tid": 2338710, "ts": 6410534303159.959, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534303163.874, "dur": 91.318, + "args": { + "External id": 1416028,"Sequence number": 15109216, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18848 + } + }, + { + "ph": "s", "id": 303, "pid": 2338710, "tid": 2338710, "ts": 6410534303163.874, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303257.608, "dur": 3.867, + "args": { + "External id": 1416029,"Sequence number": 15109217, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18849 + } + }, + { + "ph": "s", "id": 302, "pid": 2338710, "tid": 2338710, "ts": 6410534303257.608, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534303301.950, "dur": 248.331, + "args": { + "External id": 1416030,"Sequence number": 15109218, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 18850 + } + }, + { + "ph": "s", "id": 301, "pid": 2338710, "tid": 2338710, "ts": 6410534303301.950, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303321.287, "dur": 2.802, + "args": { + "External id": 1416031,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303322.501, "dur": 1.461, + "args": { + "External id": 1416032,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534303327.958, "dur": 6.813, + "args": { + "External id": 1416033,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 18853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303333.001, "dur": 1.653, + "args": { + "External id": 1416034,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303333.535, "dur": 0.997, + "args": { + "External id": 1416035,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534303343.214, "dur": 8.600, + "args": { + "External id": 1416036,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534303345.839, "dur": 5.661, + "args": { + "External id": 1416037,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534303358.569, "dur": 4.972, + "args": { + "External id": 1416038,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534303369.247, "dur": 4.548, + "args": { + "External id": 1416039,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303527.968, "dur": 4.657, + "args": { + "External id": 1416040,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303529.083, "dur": 3.167, + "args": { + "External id": 1416041,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303535.488, "dur": 2.025, + "args": { + "External id": 1416042,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303536.539, "dur": 0.877, + "args": { + "External id": 1416043,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534303570.348, "dur": 105.065, + "args": { + "External id": 1416044,"Sequence number": 15109219, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534303571.542, "dur": 11.924, + "args": { + "External id": 1416045,"Sequence number": 15109219, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18865 + } + }, + { + "ph": "s", "id": 300, "pid": 2338710, "tid": 2338710, "ts": 6410534303571.542, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534303576.288, "dur": 5.794, + "args": { + "External id": 1416046,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534303578.626, "dur": 3.177, + "args": { + "External id": 1416047,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534303584.473, "dur": 90.600, + "args": { + "External id": 1416048,"Sequence number": 15109220, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303586.072, "dur": 4.523, + "args": { + "External id": 1416049,"Sequence number": 15109220, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303586.548, "dur": 3.928, + "args": { + "External id": 1416050,"Sequence number": 15109220, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18870 + } + }, + { + "ph": "s", "id": 299, "pid": 2338710, "tid": 2338710, "ts": 6410534303586.548, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534303591.394, "dur": 75.575, + "args": { + "External id": 1416051,"Sequence number": 15109221, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18871 + } + }, + { + "ph": "s", "id": 298, "pid": 2338710, "tid": 2338710, "ts": 6410534303591.394, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303669.642, "dur": 4.803, + "args": { + "External id": 1416052,"Sequence number": 15109222, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18872 + } + }, + { + "ph": "s", "id": 297, "pid": 2338710, "tid": 2338710, "ts": 6410534303669.642, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534303684.934, "dur": 72.546, + "args": { + "External id": 1416053,"Sequence number": 15109223, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534303685.358, "dur": 7.855, + "args": { + "External id": 1416054,"Sequence number": 15109223, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18874 + } + }, + { + "ph": "s", "id": 296, "pid": 2338710, "tid": 2338710, "ts": 6410534303685.358, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534303687.361, "dur": 4.608, + "args": { + "External id": 1416055,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534303691.149, "dur": 0.688, + "args": { + "External id": 1416056,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534303693.924, "dur": 63.326, + "args": { + "External id": 1416057,"Sequence number": 15109224, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303694.808, "dur": 5.403, + "args": { + "External id": 1416058,"Sequence number": 15109224, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303695.555, "dur": 4.506, + "args": { + "External id": 1416059,"Sequence number": 15109224, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18879 + } + }, + { + "ph": "s", "id": 295, "pid": 2338710, "tid": 2338710, "ts": 6410534303695.555, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534303702.970, "dur": 46.198, + "args": { + "External id": 1416060,"Sequence number": 15109225, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18880 + } + }, + { + "ph": "s", "id": 294, "pid": 2338710, "tid": 2338710, "ts": 6410534303702.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303751.391, "dur": 5.071, + "args": { + "External id": 1416061,"Sequence number": 15109226, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18881 + } + }, + { + "ph": "s", "id": 293, "pid": 2338710, "tid": 2338710, "ts": 6410534303751.391, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534303780.350, "dur": 148.692, + "args": { + "External id": 1416062,"Sequence number": 15109227, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18882 + } + }, + { + "ph": "s", "id": 292, "pid": 2338710, "tid": 2338710, "ts": 6410534303780.350, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534303817.795, "dur": 5.091, + "args": { + "External id": 1416063,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534303855.119, "dur": 62.564, + "args": { + "External id": 1416064,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534303855.771, "dur": 6.371, + "args": { + "External id": 1416065,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 18885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534303856.879, "dur": 4.355, + "args": { + "External id": 1416066,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 18886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534303858.758, "dur": 2.254, + "args": { + "External id": 1416067,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 18887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534303863.034, "dur": 54.228, + "args": { + "External id": 1416068,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 18888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534303864.175, "dur": 2.788, + "args": { + "External id": 1416069,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303865.464, "dur": 1.375, + "args": { + "External id": 1416070,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534303869.722, "dur": 43.657, + "args": { + "External id": 1416071,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 18891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534303915.644, "dur": 1.033, + "args": { + "External id": 1416072,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410534303937.420, "dur": 30.939, + "args": { + "External id": 1416073,"Sequence number": 15109228, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 18893 + } + }, + { + "ph": "s", "id": 291, "pid": 2338710, "tid": 2338710, "ts": 6410534303937.420, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534304002.308, "dur": 236.274, + "args": { + "External id": 1416074,"Sequence number": 15109229, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 18894 + } + }, + { + "ph": "s", "id": 290, "pid": 2338710, "tid": 2338710, "ts": 6410534304002.308, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534304020.836, "dur": 3.759, + "args": { + "External id": 1416075,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304021.666, "dur": 2.743, + "args": { + "External id": 1416076,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534304032.257, "dur": 8.846, + "args": { + "External id": 1416077,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534304036.960, "dur": 3.759, + "args": { + "External id": 1416078,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534304047.652, "dur": 5.118, + "args": { + "External id": 1416079,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534304222.004, "dur": 5.063, + "args": { + "External id": 1416080,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304223.409, "dur": 3.281, + "args": { + "External id": 1416081,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534304258.220, "dur": 97.659, + "args": { + "External id": 1416082,"Sequence number": 15109230, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534304259.316, "dur": 9.499, + "args": { + "External id": 1416083,"Sequence number": 15109230, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18903 + } + }, + { + "ph": "s", "id": 289, "pid": 2338710, "tid": 2338710, "ts": 6410534304259.316, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534304261.908, "dur": 5.781, + "args": { + "External id": 1416084,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534304266.043, "dur": 1.391, + "args": { + "External id": 1416085,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534304269.746, "dur": 85.841, + "args": { + "External id": 1416086,"Sequence number": 15109231, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534304271.322, "dur": 5.461, + "args": { + "External id": 1416087,"Sequence number": 15109231, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304271.896, "dur": 4.732, + "args": { + "External id": 1416088,"Sequence number": 15109231, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18908 + } + }, + { + "ph": "s", "id": 288, "pid": 2338710, "tid": 2338710, "ts": 6410534304271.896, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534304277.495, "dur": 71.486, + "args": { + "External id": 1416089,"Sequence number": 15109232, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18909 + } + }, + { + "ph": "s", "id": 287, "pid": 2338710, "tid": 2338710, "ts": 6410534304277.495, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304351.358, "dur": 3.574, + "args": { + "External id": 1416090,"Sequence number": 15109233, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18910 + } + }, + { + "ph": "s", "id": 286, "pid": 2338710, "tid": 2338710, "ts": 6410534304351.358, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534304364.868, "dur": 79.278, + "args": { + "External id": 1416091,"Sequence number": 15109234, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534304365.381, "dur": 6.744, + "args": { + "External id": 1416092,"Sequence number": 15109234, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18912 + } + }, + { + "ph": "s", "id": 285, "pid": 2338710, "tid": 2338710, "ts": 6410534304365.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534304367.184, "dur": 3.705, + "args": { + "External id": 1416093,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534304370.230, "dur": 0.522, + "args": { + "External id": 1416094,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534304374.926, "dur": 68.922, + "args": { + "External id": 1416095,"Sequence number": 15109235, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534304375.922, "dur": 4.544, + "args": { + "External id": 1416096,"Sequence number": 15109235, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304377.046, "dur": 3.286, + "args": { + "External id": 1416097,"Sequence number": 15109235, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18917 + } + }, + { + "ph": "s", "id": 284, "pid": 2338710, "tid": 2338710, "ts": 6410534304377.046, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534304381.099, "dur": 53.037, + "args": { + "External id": 1416098,"Sequence number": 15109236, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18918 + } + }, + { + "ph": "s", "id": 283, "pid": 2338710, "tid": 2338710, "ts": 6410534304381.099, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304436.927, "dur": 6.187, + "args": { + "External id": 1416099,"Sequence number": 15109237, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18919 + } + }, + { + "ph": "s", "id": 282, "pid": 2338710, "tid": 2338710, "ts": 6410534304436.927, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534304456.803, "dur": 63.119, + "args": { + "External id": 1416100,"Sequence number": 15109238, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534304457.535, "dur": 5.468, + "args": { + "External id": 1416101,"Sequence number": 15109238, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18921 + } + }, + { + "ph": "s", "id": 281, "pid": 2338710, "tid": 2338710, "ts": 6410534304457.535, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534304459.415, "dur": 2.338, + "args": { + "External id": 1416102,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534304461.098, "dur": 0.528, + "args": { + "External id": 1416103,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534304463.676, "dur": 56.016, + "args": { + "External id": 1416104,"Sequence number": 15109239, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534304467.050, "dur": 4.880, + "args": { + "External id": 1416105,"Sequence number": 15109239, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304468.012, "dur": 3.787, + "args": { + "External id": 1416106,"Sequence number": 15109239, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18926 + } + }, + { + "ph": "s", "id": 280, "pid": 2338710, "tid": 2338710, "ts": 6410534304468.012, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534304472.642, "dur": 41.980, + "args": { + "External id": 1416107,"Sequence number": 15109240, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18927 + } + }, + { + "ph": "s", "id": 279, "pid": 2338710, "tid": 2338710, "ts": 6410534304472.642, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304516.550, "dur": 2.866, + "args": { + "External id": 1416108,"Sequence number": 15109241, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18928 + } + }, + { + "ph": "s", "id": 278, "pid": 2338710, "tid": 2338710, "ts": 6410534304516.550, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534304539.147, "dur": 3.702, + "args": { + "External id": 1416109,"Sequence number": 15109242, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304539.955, "dur": 2.758, + "args": { + "External id": 1416110,"Sequence number": 15109242, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18930 + } + }, + { + "ph": "s", "id": 277, "pid": 2338710, "tid": 2338710, "ts": 6410534304539.955, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534304549.504, "dur": 5.219, + "args": { + "External id": 1416111,"Sequence number": 15109243, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304550.781, "dur": 3.782, + "args": { + "External id": 1416112,"Sequence number": 15109243, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18932 + } + }, + { + "ph": "s", "id": 276, "pid": 2338710, "tid": 2338710, "ts": 6410534304550.781, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534304558.778, "dur": 4.414, + "args": { + "External id": 1416113,"Sequence number": 15109244, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534304559.467, "dur": 3.567, + "args": { + "External id": 1416114,"Sequence number": 15109244, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18934 + } + }, + { + "ph": "s", "id": 275, "pid": 2338710, "tid": 2338710, "ts": 6410534304559.467, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534304593.706, "dur": 158.733, + "args": { + "External id": 1416115,"Sequence number": 15109245, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18935 + } + }, + { + "ph": "s", "id": 274, "pid": 2338710, "tid": 2338710, "ts": 6410534304593.706, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534304613.763, "dur": 8.727, + "args": { + "External id": 1416116,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534304616.392, "dur": 5.734, + "args": { + "External id": 1416117,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534304765.470, "dur": 105.183, + "args": { + "External id": 1416118,"Sequence number": 15109246, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18938 + } + }, + { + "ph": "s", "id": 273, "pid": 2338710, "tid": 2338710, "ts": 6410534304765.470, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534304778.637, "dur": 7.958, + "args": { + "External id": 1416119,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 18939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534304780.540, "dur": 5.744, + "args": { + "External id": 1416120,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338710, "tid": 2338710, + "ts": 6410534304900.212, "dur": 212.832, + "args": { + "External id": 1416121,"Sequence number": 15109247, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 18941 + } + }, + { + "ph": "s", "id": 272, "pid": 2338710, "tid": 2338710, "ts": 6410534304900.212, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534304924.904, "dur": 121.048, + "args": { + "External id": 1416122,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534304969.023, "dur": 6.691, + "args": { + "External id": 1416123,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534304971.771, "dur": 3.453, + "args": { + "External id": 1416124,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534304978.339, "dur": 3.389, + "args": { + "External id": 1416125,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534304986.960, "dur": 0.912, + "args": { + "External id": 1416126,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534304990.035, "dur": 4.822, + "args": { + "External id": 1416127,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338710, "tid": 2338710, + "ts": 6410534305093.979, "dur": 5.165, + "args": { + "External id": 1416128,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 18948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305120.086, "dur": 6.577, + "args": { + "External id": 1416129,"Sequence number": 15109248, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305121.531, "dur": 4.940, + "args": { + "External id": 1416130,"Sequence number": 15109248, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18950 + } + }, + { + "ph": "s", "id": 271, "pid": 2338710, "tid": 2338710, "ts": 6410534305121.531, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534305140.001, "dur": 110.998, + "args": { + "External id": 1416131,"Sequence number": 15109249, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534305141.213, "dur": 10.724, + "args": { + "External id": 1416132,"Sequence number": 15109249, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18952 + } + }, + { + "ph": "s", "id": 270, "pid": 2338710, "tid": 2338710, "ts": 6410534305141.213, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534305144.237, "dur": 6.399, + "args": { + "External id": 1416133,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534305148.839, "dur": 1.543, + "args": { + "External id": 1416134,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534305153.378, "dur": 97.355, + "args": { + "External id": 1416135,"Sequence number": 15109250, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305155.029, "dur": 3.772, + "args": { + "External id": 1416136,"Sequence number": 15109250, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305156.121, "dur": 2.544, + "args": { + "External id": 1416137,"Sequence number": 15109250, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18957 + } + }, + { + "ph": "s", "id": 269, "pid": 2338710, "tid": 2338710, "ts": 6410534305156.121, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534305162.042, "dur": 81.838, + "args": { + "External id": 1416138,"Sequence number": 15109251, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18958 + } + }, + { + "ph": "s", "id": 268, "pid": 2338710, "tid": 2338710, "ts": 6410534305162.042, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305246.186, "dur": 3.843, + "args": { + "External id": 1416139,"Sequence number": 15109252, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18959 + } + }, + { + "ph": "s", "id": 267, "pid": 2338710, "tid": 2338710, "ts": 6410534305246.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534305288.323, "dur": 235.749, + "args": { + "External id": 1416140,"Sequence number": 15109253, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 18960 + } + }, + { + "ph": "s", "id": 266, "pid": 2338710, "tid": 2338710, "ts": 6410534305288.323, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305305.899, "dur": 4.593, + "args": { + "External id": 1416141,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305308.812, "dur": 1.502, + "args": { + "External id": 1416142,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338710, "tid": 2338710, + "ts": 6410534305314.397, "dur": 2.932, + "args": { + "External id": 1416143,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 18963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305315.408, "dur": 1.807, + "args": { + "External id": 1416144,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305316.425, "dur": 0.681, + "args": { + "External id": 1416145,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534305325.166, "dur": 7.748, + "args": { + "External id": 1416146,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534305327.687, "dur": 4.903, + "args": { + "External id": 1416147,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534305341.127, "dur": 5.470, + "args": { + "External id": 1416148,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534305352.032, "dur": 3.508, + "args": { + "External id": 1416149,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305501.205, "dur": 3.960, + "args": { + "External id": 1416150,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305502.275, "dur": 2.457, + "args": { + "External id": 1416151,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305508.024, "dur": 1.875, + "args": { + "External id": 1416152,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305508.942, "dur": 0.851, + "args": { + "External id": 1416153,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534305542.461, "dur": 99.654, + "args": { + "External id": 1416154,"Sequence number": 15109254, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534305543.482, "dur": 9.576, + "args": { + "External id": 1416155,"Sequence number": 15109254, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18975 + } + }, + { + "ph": "s", "id": 265, "pid": 2338710, "tid": 2338710, "ts": 6410534305543.482, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534305547.875, "dur": 4.072, + "args": { + "External id": 1416156,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534305550.127, "dur": 1.587, + "args": { + "External id": 1416157,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534305553.914, "dur": 87.925, + "args": { + "External id": 1416158,"Sequence number": 15109255, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305555.510, "dur": 6.546, + "args": { + "External id": 1416159,"Sequence number": 15109255, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305559.009, "dur": 2.923, + "args": { + "External id": 1416160,"Sequence number": 15109255, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18980 + } + }, + { + "ph": "s", "id": 264, "pid": 2338710, "tid": 2338710, "ts": 6410534305559.009, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534305563.082, "dur": 71.873, + "args": { + "External id": 1416161,"Sequence number": 15109256, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18981 + } + }, + { + "ph": "s", "id": 263, "pid": 2338710, "tid": 2338710, "ts": 6410534305563.082, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305637.164, "dur": 4.122, + "args": { + "External id": 1416162,"Sequence number": 15109257, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18982 + } + }, + { + "ph": "s", "id": 262, "pid": 2338710, "tid": 2338710, "ts": 6410534305637.164, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534305650.488, "dur": 84.776, + "args": { + "External id": 1416163,"Sequence number": 15109258, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534305651.222, "dur": 10.767, + "args": { + "External id": 1416164,"Sequence number": 15109258, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18984 + } + }, + { + "ph": "s", "id": 261, "pid": 2338710, "tid": 2338710, "ts": 6410534305651.222, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534305658.202, "dur": 2.563, + "args": { + "External id": 1416165,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534305659.951, "dur": 0.644, + "args": { + "External id": 1416166,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534305662.806, "dur": 72.209, + "args": { + "External id": 1416167,"Sequence number": 15109259, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305664.112, "dur": 6.583, + "args": { + "External id": 1416168,"Sequence number": 15109259, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305665.148, "dur": 5.411, + "args": { + "External id": 1416169,"Sequence number": 15109259, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18989 + } + }, + { + "ph": "s", "id": 260, "pid": 2338710, "tid": 2338710, "ts": 6410534305665.148, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534305671.465, "dur": 55.602, + "args": { + "External id": 1416170,"Sequence number": 15109260, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18990 + } + }, + { + "ph": "s", "id": 259, "pid": 2338710, "tid": 2338710, "ts": 6410534305671.465, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305728.932, "dur": 5.484, + "args": { + "External id": 1416171,"Sequence number": 15109261, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18991 + } + }, + { + "ph": "s", "id": 258, "pid": 2338710, "tid": 2338710, "ts": 6410534305728.932, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534305756.717, "dur": 151.335, + "args": { + "External id": 1416172,"Sequence number": 15109262, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18992 + } + }, + { + "ph": "s", "id": 257, "pid": 2338710, "tid": 2338710, "ts": 6410534305756.717, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534305796.805, "dur": 4.616, + "args": { + "External id": 1416173,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534305832.077, "dur": 62.957, + "args": { + "External id": 1416174,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534305833.138, "dur": 5.977, + "args": { + "External id": 1416175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 18995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534305834.215, "dur": 4.077, + "args": { + "External id": 1416176,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 18996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534305837.479, "dur": 0.640, + "args": { + "External id": 1416177,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 18997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534305839.958, "dur": 54.619, + "args": { + "External id": 1416178,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 18998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338710, "tid": 2338710, + "ts": 6410534305841.384, "dur": 4.143, + "args": { + "External id": 1416179,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305844.508, "dur": 0.911, + "args": { + "External id": 1416180,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 19000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534305846.238, "dur": 44.465, + "args": { + "External id": 1416181,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 19001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338710, "tid": 2338710, + "ts": 6410534305893.006, "dur": 1.002, + "args": { + "External id": 1416182,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410534305916.667, "dur": 25.332, + "args": { + "External id": 1416183,"Sequence number": 15109263, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 19003 + } + }, + { + "ph": "s", "id": 256, "pid": 2338710, "tid": 2338710, "ts": 6410534305916.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338710, "tid": 2338710, + "ts": 6410534305960.172, "dur": 43.725, + "args": { + "External id": 1416184,"Sequence number": 15109264, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "-2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1]], []], "Input Dims": [[[8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096]], []], "Ev Idx": 19004 + } + }, + { + "ph": "s", "id": 255, "pid": 2338710, "tid": 2338710, "ts": 6410534305960.172, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338710, "tid": 2338710, + "ts": 6410534305968.293, "dur": 31.068, + "args": { + "External id": 1416185,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1]], []], "Input Dims": [[[8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096]], []], "Ev Idx": 19005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534306001.282, "dur": 1.220, + "args": { + "External id": 1416186,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 16384], []], "Ev Idx": 19006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338710, "tid": 2338710, + "ts": 6410534306038.539, "dur": 87.375, + "args": { + "External id": 1416187,"Record function id": 0, "Ev Idx": 19007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 2338710, "tid": 2338710, + "ts": 6410534306128.573, "dur": 206.214, + "args": { + "External id": 1416188,"Record function id": 0, "Ev Idx": 19008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534306167.867, "dur": 158.268, + "args": { + "External id": 1416189,"Sequence number": 15109265, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1], [67108864, 16384, 4096, 1]], "Input Dims": [[4096], [8, 4096, 4, 4096]], "Ev Idx": 19009 + } + }, + { + "ph": "s", "id": 254, "pid": 2338710, "tid": 2338710, "ts": 6410534306167.867, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338710, "tid": 2338710, + "ts": 6410534306242.247, "dur": 44.868, + "args": { + "External id": 1416190,"kernel_hash": "c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/7z/c7zx2vpbs74pgqq3nrkkn5rgfu7zq6men4epnxhpm4uojx46qomi.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[131072, 4096], [131072, 4096], [4096], [131072], [], [], [], [], [], [], [], [], []], "Ev Idx": 19010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410534306434.267, "dur": 64.090, + "args": { + "External id": 1416191,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534306437.715, "dur": 6.409, + "args": { + "External id": 1416192,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306464.529, "dur": 33.510, + "args": { + "External id": 1416193,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 19013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306467.297, "dur": 30.215, + "args": { + "External id": 1416194,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 19014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410534306505.280, "dur": 19.634, + "args": { + "External id": 1416195,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534306506.184, "dur": 2.109, + "args": { + "External id": 1416196,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306508.880, "dur": 15.790, + "args": { + "External id": 1416197,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 19017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306511.811, "dur": 12.453, + "args": { + "External id": 1416198,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 19018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410534306527.367, "dur": 16.167, + "args": { + "External id": 1416199,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534306528.272, "dur": 2.016, + "args": { + "External id": 1416200,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306530.843, "dur": 12.445, + "args": { + "External id": 1416201,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 19021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306531.213, "dur": 11.594, + "args": { + "External id": 1416202,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 19022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534306554.191, "dur": 0.752, + "args": { + "External id": 1416203,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], [], []], "Ev Idx": 19023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338710, "tid": 2338710, + "ts": 6410534306563.019, "dur": 12.689, + "args": { + "External id": 1416204,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "5", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 19024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306571.202, "dur": 2.300, + "args": { + "External id": 1416205,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 19025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306582.446, "dur": 7.095, + "args": { + "External id": 1416206,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 19026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306586.889, "dur": 0.755, + "args": { + "External id": 1416207,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 19027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306590.708, "dur": 3.264, + "args": { + "External id": 1416208,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 19028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306592.771, "dur": 0.424, + "args": { + "External id": 1416209,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 19029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306595.432, "dur": 2.815, + "args": { + "External id": 1416210,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 19030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306597.326, "dur": 0.368, + "args": { + "External id": 1416211,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 19031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306600.947, "dur": 5.067, + "args": { + "External id": 1416212,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 4], [], [], [], []], "Ev Idx": 19032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306602.697, "dur": 2.623, + "args": { + "External id": 1416213,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 4], [], [], []], "Ev Idx": 19033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306606.917, "dur": 3.216, + "args": { + "External id": 1416214,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 4], [], [], [], []], "Ev Idx": 19034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306609.042, "dur": 0.400, + "args": { + "External id": 1416215,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 4], [], [], []], "Ev Idx": 19035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306611.024, "dur": 2.514, + "args": { + "External id": 1416216,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4096, 4], [], [], [], []], "Ev Idx": 19036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306612.672, "dur": 0.332, + "args": { + "External id": 1416217,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4096, 4], [], [], []], "Ev Idx": 19037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534306618.384, "dur": 5.277, + "args": { + "External id": 1416218,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4096, 4], [], []], "Ev Idx": 19038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306622.497, "dur": 0.358, + "args": { + "External id": 1416219,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4096, 4], [], [], []], "Ev Idx": 19039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306627.711, "dur": 2.857, + "args": { + "External id": 1416220,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 19040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306629.456, "dur": 0.480, + "args": { + "External id": 1416221,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410534306634.140, "dur": 9.234, + "args": { + "External id": 1416222,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 19042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306641.768, "dur": 0.543, + "args": { + "External id": 1416223,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306644.511, "dur": 1.904, + "args": { + "External id": 1416224,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 19044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306645.630, "dur": 0.237, + "args": { + "External id": 1416225,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 19045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306648.913, "dur": 6.550, + "args": { + "External id": 1416226,"Sequence number": 15109266, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19046 + } + }, + { + "ph": "s", "id": 253, "pid": 2338710, "tid": 2338710, "ts": 6410534306648.913, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306653.253, "dur": 0.494, + "args": { + "External id": 1416227,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306658.667, "dur": 6.733, + "args": { + "External id": 1416228,"Sequence number": 15109267, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19048 + } + }, + { + "ph": "s", "id": 252, "pid": 2338710, "tid": 2338710, "ts": 6410534306658.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306662.337, "dur": 2.208, + "args": { + "External id": 1416229,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410534306666.381, "dur": 5.128, + "args": { + "External id": 1416230,"Sequence number": 15109268, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 19050 + } + }, + { + "ph": "s", "id": 251, "pid": 2338710, "tid": 2338710, "ts": 6410534306666.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306670.208, "dur": 0.416, + "args": { + "External id": 1416231,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534306672.481, "dur": 5.539, + "args": { + "External id": 1416232,"Sequence number": 15109269, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 19052 + } + }, + { + "ph": "s", "id": 250, "pid": 2338710, "tid": 2338710, "ts": 6410534306672.481, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306676.782, "dur": 0.377, + "args": { + "External id": 1416233,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 19053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410534306681.780, "dur": 36.066, + "args": { + "External id": 1416234,"Sequence number": 15109270, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410534306685.587, "dur": 31.944, + "args": { + "External id": 1416235,"Sequence number": 15109270, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534306688.424, "dur": 6.210, + "args": { + "External id": 1416236,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 19056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534306689.946, "dur": 4.125, + "args": { + "External id": 1416237,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306696.022, "dur": 21.065, + "args": { + "External id": 1416238,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 19058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534306744.753, "dur": 4.392, + "args": { + "External id": 1416239,"Sequence number": 15109270, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 19059 + } + }, + { + "ph": "s", "id": 249, "pid": 2338710, "tid": 2338710, "ts": 6410534306744.753, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534306751.259, "dur": 1.040, + "args": { + "External id": 1416240,"Sequence number": 15109271, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534306780.508, "dur": 130543.708, + "args": { + "External id": 1416241,"Sequence number": 15109271, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 19061 + } + }, + { + "ph": "s", "id": 248, "pid": 2338710, "tid": 2338710, "ts": 6410534306780.508, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410534306793.277, "dur": 26.368, + "args": { + "External id": 1416242,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410534306793.816, "dur": 25.612, + "args": { + "External id": 1416243,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534306795.375, "dur": 5.358, + "args": { + "External id": 1416244,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534306797.649, "dur": 2.680, + "args": { + "External id": 1416245,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306801.578, "dur": 17.256, + "args": { + "External id": 1416246,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 19066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534306837.161, "dur": 23.339, + "args": { + "External id": 1416247,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534306838.417, "dur": 5.920, + "args": { + "External id": 1416248,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306840.705, "dur": 3.337, + "args": { + "External id": 1416249,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306845.074, "dur": 15.227, + "args": { + "External id": 1416250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306846.053, "dur": 13.941, + "args": { + "External id": 1416251,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534306863.451, "dur": 20.531, + "args": { + "External id": 1416252,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534306864.105, "dur": 8.549, + "args": { + "External id": 1416253,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306867.428, "dur": 5.013, + "args": { + "External id": 1416254,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306873.164, "dur": 10.621, + "args": { + "External id": 1416255,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306873.533, "dur": 9.846, + "args": { + "External id": 1416256,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 19076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410534306889.294, "dur": 15.599, + "args": { + "External id": 1416257,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534306890.220, "dur": 2.919, + "args": { + "External id": 1416258,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306893.664, "dur": 10.965, + "args": { + "External id": 1416259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 19079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306894.191, "dur": 10.067, + "args": { + "External id": 1416260,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410534306913.260, "dur": 30.547, + "args": { + "External id": 1416261,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534306948.351, "dur": 56.715, + "args": { + "External id": 1416262,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534306951.066, "dur": 53.542, + "args": { + "External id": 1416263,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306958.824, "dur": 0.702, + "args": { + "External id": 1416264,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534306962.958, "dur": 22.517, + "args": { + "External id": 1416265,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534306964.410, "dur": 20.862, + "args": { + "External id": 1416266,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 19086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534306966.811, "dur": 2.657, + "args": { + "External id": 1416267,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534306970.283, "dur": 14.594, + "args": { + "External id": 1416268,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 19088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410534307012.561, "dur": 124131.628, + "args": { + "External id": 1416269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410534307014.165, "dur": 124124.759, + "args": { + "External id": 1416270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534431178.649, "dur": 17.342, + "args": { + "External id": 1416271,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534431189.617, "dur": 3.001, + "args": { + "External id": 1416272,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534431203.869, "dur": 141.442, + "args": { + "External id": 1416273,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534431205.719, "dur": 8.337, + "args": { + "External id": 1416274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534431209.237, "dur": 3.911, + "args": { + "External id": 1416275,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534431211.763, "dur": 1.097, + "args": { + "External id": 1416276,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534431215.440, "dur": 129.007, + "args": { + "External id": 1416277,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534431220.198, "dur": 122.998, + "args": { + "External id": 1416278,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534431351.061, "dur": 5.510, + "args": { + "External id": 1416279,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534431353.826, "dur": 0.740, + "args": { + "External id": 1416280,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534431369.167, "dur": 4.780, + "args": { + "External id": 1416281,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534431388.304, "dur": 11.467, + "args": { + "External id": 1416282,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534431391.306, "dur": 8.110, + "args": { + "External id": 1416283,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534431578.862, "dur": 264.902, + "args": { + "External id": 1416284,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534431584.597, "dur": 3.306, + "args": { + "External id": 1416285,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534431590.260, "dur": 252.972, + "args": { + "External id": 1416286,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534431593.303, "dur": 0.777, + "args": { + "External id": 1416287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534431596.765, "dur": 35.875, + "args": { + "External id": 1416288,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534431634.873, "dur": 6.532, + "args": { + "External id": 1416289,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534431639.822, "dur": 1.029, + "args": { + "External id": 1416290,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534431643.619, "dur": 33.075, + "args": { + "External id": 1416291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534431645.279, "dur": 1.310, + "args": { + "External id": 1416292,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534431651.011, "dur": 25.309, + "args": { + "External id": 1416293,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534431655.938, "dur": 3.460, + "args": { + "External id": 1416294,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534431678.876, "dur": 29.038, + "args": { + "External id": 1416295,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534431710.776, "dur": 21.949, + "args": { + "External id": 1416296,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534431736.656, "dur": 19.616, + "args": { + "External id": 1416297,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534431758.520, "dur": 19.427, + "args": { + "External id": 1416298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534431780.698, "dur": 25.953, + "args": { + "External id": 1416299,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534431783.296, "dur": 1.721, + "args": { + "External id": 1416300,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534431789.023, "dur": 0.764, + "args": { + "External id": 1416301,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534431809.169, "dur": 17.709, + "args": { + "External id": 1416302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534431828.845, "dur": 13.137, + "args": { + "External id": 1416303,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534431852.311, "dur": 2.572, + "args": { + "External id": 1416304,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534431863.523, "dur": 4.107, + "args": { + "External id": 1416305,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534431866.199, "dur": 0.395, + "args": { + "External id": 1416306,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534431958.980, "dur": 84.810, + "args": { + "External id": 1416307,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534432049.632, "dur": 44.313, + "args": { + "External id": 1416308,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432089.932, "dur": 1.374, + "args": { + "External id": 1416309,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432095.946, "dur": 38.904, + "args": { + "External id": 1416310,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534432141.991, "dur": 7.135, + "args": { + "External id": 1416311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534432143.994, "dur": 4.322, + "args": { + "External id": 1416312,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432146.412, "dur": 1.651, + "args": { + "External id": 1416313,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534432153.699, "dur": 66.996, + "args": { + "External id": 1416314,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534432157.554, "dur": 62.429, + "args": { + "External id": 1416315,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432226.510, "dur": 21.441, + "args": { + "External id": 1416316,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534432256.823, "dur": 4.845, + "args": { + "External id": 1416317,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432260.119, "dur": 0.642, + "args": { + "External id": 1416318,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534432266.783, "dur": 51.220, + "args": { + "External id": 1416319,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534432267.984, "dur": 5.519, + "args": { + "External id": 1416320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534432268.779, "dur": 4.087, + "args": { + "External id": 1416321,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432271.965, "dur": 0.747, + "args": { + "External id": 1416322,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534432274.378, "dur": 43.141, + "args": { + "External id": 1416323,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534432275.116, "dur": 41.724, + "args": { + "External id": 1416324,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534432322.843, "dur": 6.076, + "args": { + "External id": 1416325,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432325.191, "dur": 2.364, + "args": { + "External id": 1416326,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534432336.034, "dur": 2.147, + "args": { + "External id": 1416327,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534432349.965, "dur": 7.439, + "args": { + "External id": 1416328,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534432352.238, "dur": 4.842, + "args": { + "External id": 1416329,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534432491.054, "dur": 201.716, + "args": { + "External id": 1416330,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534432493.589, "dur": 2.903, + "args": { + "External id": 1416331,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534432498.956, "dur": 193.287, + "args": { + "External id": 1416332,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534432500.583, "dur": 0.486, + "args": { + "External id": 1416333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534432502.150, "dur": 26.926, + "args": { + "External id": 1416334,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534432533.406, "dur": 3.471, + "args": { + "External id": 1416335,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432535.447, "dur": 1.090, + "args": { + "External id": 1416336,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534432537.949, "dur": 28.365, + "args": { + "External id": 1416337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534432539.593, "dur": 3.597, + "args": { + "External id": 1416338,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534432544.587, "dur": 21.413, + "args": { + "External id": 1416339,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432549.425, "dur": 2.764, + "args": { + "External id": 1416340,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534432568.103, "dur": 23.769, + "args": { + "External id": 1416341,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432593.844, "dur": 14.069, + "args": { + "External id": 1416342,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534432610.956, "dur": 14.068, + "args": { + "External id": 1416343,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432626.673, "dur": 13.501, + "args": { + "External id": 1416344,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534432642.116, "dur": 22.903, + "args": { + "External id": 1416345,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432646.727, "dur": 1.925, + "args": { + "External id": 1416346,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432650.686, "dur": 0.674, + "args": { + "External id": 1416347,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432666.667, "dur": 12.333, + "args": { + "External id": 1416348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432680.263, "dur": 10.642, + "args": { + "External id": 1416349,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534432700.967, "dur": 2.820, + "args": { + "External id": 1416350,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534432713.869, "dur": 4.239, + "args": { + "External id": 1416351,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432716.548, "dur": 0.588, + "args": { + "External id": 1416352,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534432796.330, "dur": 64.416, + "args": { + "External id": 1416353,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534432865.774, "dur": 4.930, + "args": { + "External id": 1416354,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432868.792, "dur": 0.794, + "args": { + "External id": 1416355,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432872.095, "dur": 28.078, + "args": { + "External id": 1416356,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534432905.144, "dur": 7.475, + "args": { + "External id": 1416357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534432906.741, "dur": 5.095, + "args": { + "External id": 1416358,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432910.835, "dur": 0.826, + "args": { + "External id": 1416359,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534432915.400, "dur": 44.525, + "args": { + "External id": 1416360,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534432916.641, "dur": 42.675, + "args": { + "External id": 1416361,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534432963.840, "dur": 16.274, + "args": { + "External id": 1416362,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534432986.061, "dur": 7.522, + "args": { + "External id": 1416363,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534432991.929, "dur": 0.715, + "args": { + "External id": 1416364,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534432997.967, "dur": 49.471, + "args": { + "External id": 1416365,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534433001.008, "dur": 4.926, + "args": { + "External id": 1416366,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534433001.859, "dur": 3.494, + "args": { + "External id": 1416367,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433004.489, "dur": 0.678, + "args": { + "External id": 1416368,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534433007.041, "dur": 39.987, + "args": { + "External id": 1416369,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534433007.832, "dur": 38.682, + "args": { + "External id": 1416370,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534433051.321, "dur": 40.828, + "args": { + "External id": 1416371,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433089.374, "dur": 0.864, + "args": { + "External id": 1416372,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534433102.551, "dur": 2.056, + "args": { + "External id": 1416373,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534433113.374, "dur": 9.258, + "args": { + "External id": 1416374,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534433115.854, "dur": 6.480, + "args": { + "External id": 1416375,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534433228.857, "dur": 275.231, + "args": { + "External id": 1416376,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534433231.350, "dur": 2.221, + "args": { + "External id": 1416377,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534433235.465, "dur": 268.165, + "args": { + "External id": 1416378,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534433241.095, "dur": 0.300, + "args": { + "External id": 1416379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534433242.649, "dur": 23.759, + "args": { + "External id": 1416380,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534433268.088, "dur": 3.395, + "args": { + "External id": 1416381,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433270.250, "dur": 0.965, + "args": { + "External id": 1416382,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534433272.501, "dur": 31.117, + "args": { + "External id": 1416383,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534433275.295, "dur": 1.209, + "args": { + "External id": 1416384,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534433277.739, "dur": 25.515, + "args": { + "External id": 1416385,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534433280.507, "dur": 3.122, + "args": { + "External id": 1416386,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534433304.948, "dur": 37.440, + "args": { + "External id": 1416387,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534433344.415, "dur": 39.464, + "args": { + "External id": 1416388,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534433388.368, "dur": 42.057, + "args": { + "External id": 1416389,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534433432.826, "dur": 17.444, + "args": { + "External id": 1416390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534433452.287, "dur": 22.215, + "args": { + "External id": 1416391,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534433454.408, "dur": 2.067, + "args": { + "External id": 1416392,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433458.345, "dur": 0.798, + "args": { + "External id": 1416393,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534433476.295, "dur": 12.166, + "args": { + "External id": 1416394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534433492.012, "dur": 10.418, + "args": { + "External id": 1416395,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534433512.109, "dur": 2.783, + "args": { + "External id": 1416396,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534433524.597, "dur": 4.196, + "args": { + "External id": 1416397,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433527.299, "dur": 0.638, + "args": { + "External id": 1416398,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534433601.731, "dur": 62.516, + "args": { + "External id": 1416399,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534433669.523, "dur": 6.782, + "args": { + "External id": 1416400,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433672.767, "dur": 2.232, + "args": { + "External id": 1416401,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534433677.889, "dur": 26.956, + "args": { + "External id": 1416402,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534433711.941, "dur": 5.118, + "args": { + "External id": 1416403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534433713.456, "dur": 2.908, + "args": { + "External id": 1416404,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433715.533, "dur": 0.666, + "args": { + "External id": 1416405,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534433719.911, "dur": 43.662, + "args": { + "External id": 1416406,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534433721.123, "dur": 41.862, + "args": { + "External id": 1416407,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534433767.319, "dur": 14.105, + "args": { + "External id": 1416408,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534433787.332, "dur": 6.297, + "args": { + "External id": 1416409,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433791.822, "dur": 0.758, + "args": { + "External id": 1416410,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534433798.039, "dur": 47.700, + "args": { + "External id": 1416411,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534433798.900, "dur": 3.383, + "args": { + "External id": 1416412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534433799.589, "dur": 2.140, + "args": { + "External id": 1416413,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433801.008, "dur": 0.607, + "args": { + "External id": 1416414,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534433803.059, "dur": 42.265, + "args": { + "External id": 1416415,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534433805.836, "dur": 38.737, + "args": { + "External id": 1416416,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534433849.863, "dur": 4.409, + "args": { + "External id": 1416417,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433852.148, "dur": 0.782, + "args": { + "External id": 1416418,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534433859.421, "dur": 1.544, + "args": { + "External id": 1416419,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534433868.762, "dur": 8.803, + "args": { + "External id": 1416420,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534433871.202, "dur": 6.099, + "args": { + "External id": 1416421,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534433965.843, "dur": 232.747, + "args": { + "External id": 1416422,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534433967.729, "dur": 3.401, + "args": { + "External id": 1416423,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534433972.881, "dur": 225.045, + "args": { + "External id": 1416424,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534433974.479, "dur": 0.283, + "args": { + "External id": 1416425,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534433975.709, "dur": 19.284, + "args": { + "External id": 1416426,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534433996.711, "dur": 3.886, + "args": { + "External id": 1416427,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534433999.917, "dur": 0.492, + "args": { + "External id": 1416428,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534434001.555, "dur": 21.985, + "args": { + "External id": 1416429,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534434002.832, "dur": 1.393, + "args": { + "External id": 1416430,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534434007.883, "dur": 15.386, + "args": { + "External id": 1416431,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434010.269, "dur": 2.313, + "args": { + "External id": 1416432,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534434025.360, "dur": 23.323, + "args": { + "External id": 1416433,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434050.036, "dur": 52.140, + "args": { + "External id": 1416434,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534434106.312, "dur": 16.536, + "args": { + "External id": 1416435,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434124.199, "dur": 13.702, + "args": { + "External id": 1416436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534434140.797, "dur": 25.643, + "args": { + "External id": 1416437,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434143.112, "dur": 2.026, + "args": { + "External id": 1416438,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434147.662, "dur": 2.001, + "args": { + "External id": 1416439,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434170.511, "dur": 12.564, + "args": { + "External id": 1416440,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434184.503, "dur": 12.373, + "args": { + "External id": 1416441,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534434206.573, "dur": 2.404, + "args": { + "External id": 1416442,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534434218.080, "dur": 4.548, + "args": { + "External id": 1416443,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434220.974, "dur": 0.806, + "args": { + "External id": 1416444,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534434289.385, "dur": 59.628, + "args": { + "External id": 1416445,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534434353.799, "dur": 5.102, + "args": { + "External id": 1416446,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434356.873, "dur": 0.750, + "args": { + "External id": 1416447,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434362.668, "dur": 27.259, + "args": { + "External id": 1416448,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534434394.468, "dur": 5.995, + "args": { + "External id": 1416449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534434396.236, "dur": 3.464, + "args": { + "External id": 1416450,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434398.356, "dur": 1.188, + "args": { + "External id": 1416451,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534434403.105, "dur": 60.309, + "args": { + "External id": 1416452,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534434404.379, "dur": 57.806, + "args": { + "External id": 1416453,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434468.630, "dur": 16.298, + "args": { + "External id": 1416454,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534434493.397, "dur": 5.054, + "args": { + "External id": 1416455,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434496.296, "dur": 0.921, + "args": { + "External id": 1416456,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534434502.730, "dur": 50.509, + "args": { + "External id": 1416457,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534434503.586, "dur": 6.089, + "args": { + "External id": 1416458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534434504.570, "dur": 4.507, + "args": { + "External id": 1416459,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434506.169, "dur": 2.779, + "args": { + "External id": 1416460,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534434512.245, "dur": 40.538, + "args": { + "External id": 1416461,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534434513.057, "dur": 39.122, + "args": { + "External id": 1416462,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534434557.217, "dur": 4.093, + "args": { + "External id": 1416463,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434559.661, "dur": 0.530, + "args": { + "External id": 1416464,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534434567.588, "dur": 1.701, + "args": { + "External id": 1416465,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534434577.411, "dur": 8.623, + "args": { + "External id": 1416466,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534434581.846, "dur": 3.886, + "args": { + "External id": 1416467,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534434671.272, "dur": 177.467, + "args": { + "External id": 1416468,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534434674.847, "dur": 1.698, + "args": { + "External id": 1416469,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534434678.291, "dur": 169.890, + "args": { + "External id": 1416470,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534434679.757, "dur": 0.452, + "args": { + "External id": 1416471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534434681.609, "dur": 19.814, + "args": { + "External id": 1416472,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534434702.764, "dur": 4.729, + "args": { + "External id": 1416473,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434706.535, "dur": 0.704, + "args": { + "External id": 1416474,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534434708.328, "dur": 22.560, + "args": { + "External id": 1416475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534434711.597, "dur": 1.240, + "args": { + "External id": 1416476,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534434714.030, "dur": 16.602, + "args": { + "External id": 1416477,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434716.295, "dur": 3.221, + "args": { + "External id": 1416478,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534434732.137, "dur": 21.073, + "args": { + "External id": 1416479,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434754.918, "dur": 13.348, + "args": { + "External id": 1416480,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534434770.757, "dur": 12.620, + "args": { + "External id": 1416481,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434784.591, "dur": 11.734, + "args": { + "External id": 1416482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534434798.418, "dur": 22.606, + "args": { + "External id": 1416483,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434802.556, "dur": 1.087, + "args": { + "External id": 1416484,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434807.990, "dur": 0.622, + "args": { + "External id": 1416485,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434822.218, "dur": 12.866, + "args": { + "External id": 1416486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534434836.110, "dur": 11.014, + "args": { + "External id": 1416487,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534434854.919, "dur": 1.709, + "args": { + "External id": 1416488,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534434865.331, "dur": 3.770, + "args": { + "External id": 1416489,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534434867.639, "dur": 0.664, + "args": { + "External id": 1416490,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534434932.239, "dur": 54.139, + "args": { + "External id": 1416491,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534435001.173, "dur": 4.835, + "args": { + "External id": 1416492,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435004.341, "dur": 0.622, + "args": { + "External id": 1416493,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435007.305, "dur": 30.396, + "args": { + "External id": 1416494,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534435041.673, "dur": 6.244, + "args": { + "External id": 1416495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534435043.165, "dur": 4.081, + "args": { + "External id": 1416496,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435044.992, "dur": 2.036, + "args": { + "External id": 1416497,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534435089.359, "dur": 51.820, + "args": { + "External id": 1416498,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534435091.059, "dur": 49.300, + "args": { + "External id": 1416499,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435146.197, "dur": 15.423, + "args": { + "External id": 1416500,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534435168.315, "dur": 4.755, + "args": { + "External id": 1416501,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435171.137, "dur": 0.673, + "args": { + "External id": 1416502,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534435177.167, "dur": 49.974, + "args": { + "External id": 1416503,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534435177.997, "dur": 6.053, + "args": { + "External id": 1416504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534435181.010, "dur": 2.377, + "args": { + "External id": 1416505,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435182.332, "dur": 0.920, + "args": { + "External id": 1416506,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534435184.696, "dur": 42.063, + "args": { + "External id": 1416507,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534435188.373, "dur": 37.754, + "args": { + "External id": 1416508,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534435231.270, "dur": 3.732, + "args": { + "External id": 1416509,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435233.372, "dur": 0.490, + "args": { + "External id": 1416510,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534435241.205, "dur": 1.565, + "args": { + "External id": 1416511,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534435252.818, "dur": 10.619, + "args": { + "External id": 1416512,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534435255.017, "dur": 8.068, + "args": { + "External id": 1416513,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534435352.741, "dur": 216.652, + "args": { + "External id": 1416514,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534435355.363, "dur": 1.902, + "args": { + "External id": 1416515,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534435359.353, "dur": 209.413, + "args": { + "External id": 1416516,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534435361.102, "dur": 0.409, + "args": { + "External id": 1416517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534435364.650, "dur": 24.514, + "args": { + "External id": 1416518,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534435391.472, "dur": 3.333, + "args": { + "External id": 1416519,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435393.753, "dur": 0.838, + "args": { + "External id": 1416520,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534435396.008, "dur": 41.065, + "args": { + "External id": 1416521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534435397.287, "dur": 1.572, + "args": { + "External id": 1416522,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534435399.979, "dur": 36.379, + "args": { + "External id": 1416523,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435404.329, "dur": 2.156, + "args": { + "External id": 1416524,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534435439.026, "dur": 24.124, + "args": { + "External id": 1416525,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435464.968, "dur": 13.856, + "args": { + "External id": 1416526,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534435481.136, "dur": 15.227, + "args": { + "External id": 1416527,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435497.822, "dur": 14.003, + "args": { + "External id": 1416528,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534435516.019, "dur": 22.831, + "args": { + "External id": 1416529,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435518.784, "dur": 1.686, + "args": { + "External id": 1416530,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435523.017, "dur": 0.591, + "args": { + "External id": 1416531,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435540.196, "dur": 12.923, + "args": { + "External id": 1416532,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435554.362, "dur": 13.136, + "args": { + "External id": 1416533,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534435576.644, "dur": 2.320, + "args": { + "External id": 1416534,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534435587.916, "dur": 3.650, + "args": { + "External id": 1416535,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435590.142, "dur": 0.541, + "args": { + "External id": 1416536,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534435660.839, "dur": 58.136, + "args": { + "External id": 1416537,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534435724.286, "dur": 5.081, + "args": { + "External id": 1416538,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435727.528, "dur": 0.731, + "args": { + "External id": 1416539,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435730.659, "dur": 27.047, + "args": { + "External id": 1416540,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534435762.684, "dur": 12.762, + "args": { + "External id": 1416541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534435764.066, "dur": 10.740, + "args": { + "External id": 1416542,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435772.812, "dur": 1.800, + "args": { + "External id": 1416543,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534435778.226, "dur": 47.665, + "args": { + "External id": 1416544,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534435779.429, "dur": 45.824, + "args": { + "External id": 1416545,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534435829.524, "dur": 14.507, + "args": { + "External id": 1416546,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534435849.847, "dur": 4.186, + "args": { + "External id": 1416547,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435852.446, "dur": 0.670, + "args": { + "External id": 1416548,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534435857.786, "dur": 49.337, + "args": { + "External id": 1416549,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534435861.240, "dur": 3.674, + "args": { + "External id": 1416550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534435862.066, "dur": 2.313, + "args": { + "External id": 1416551,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435863.401, "dur": 0.836, + "args": { + "External id": 1416552,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534435865.731, "dur": 41.055, + "args": { + "External id": 1416553,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534435866.420, "dur": 39.790, + "args": { + "External id": 1416554,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534435911.413, "dur": 4.003, + "args": { + "External id": 1416555,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534435913.695, "dur": 0.593, + "args": { + "External id": 1416556,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534435922.859, "dur": 1.516, + "args": { + "External id": 1416557,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534435932.119, "dur": 6.020, + "args": { + "External id": 1416558,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534435934.280, "dur": 3.599, + "args": { + "External id": 1416559,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534436022.636, "dur": 229.870, + "args": { + "External id": 1416560,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534436024.815, "dur": 1.975, + "args": { + "External id": 1416561,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534436029.666, "dur": 222.208, + "args": { + "External id": 1416562,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534436032.977, "dur": 0.291, + "args": { + "External id": 1416563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534436034.250, "dur": 20.521, + "args": { + "External id": 1416564,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534436094.286, "dur": 5.452, + "args": { + "External id": 1416565,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436096.781, "dur": 2.419, + "args": { + "External id": 1416566,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534436100.978, "dur": 26.283, + "args": { + "External id": 1416567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534436102.498, "dur": 2.280, + "args": { + "External id": 1416568,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534436106.070, "dur": 20.901, + "args": { + "External id": 1416569,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436109.080, "dur": 2.894, + "args": { + "External id": 1416570,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534436128.600, "dur": 25.297, + "args": { + "External id": 1416571,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436156.061, "dur": 13.493, + "args": { + "External id": 1416572,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534436174.930, "dur": 13.136, + "args": { + "External id": 1416573,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436189.454, "dur": 12.597, + "args": { + "External id": 1416574,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534436204.195, "dur": 20.392, + "args": { + "External id": 1416575,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436206.509, "dur": 1.418, + "args": { + "External id": 1416576,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436210.590, "dur": 0.514, + "args": { + "External id": 1416577,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436225.806, "dur": 11.886, + "args": { + "External id": 1416578,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436241.238, "dur": 9.396, + "args": { + "External id": 1416579,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534436260.691, "dur": 2.287, + "args": { + "External id": 1416580,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534436272.908, "dur": 4.132, + "args": { + "External id": 1416581,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436275.620, "dur": 0.615, + "args": { + "External id": 1416582,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534436345.961, "dur": 56.492, + "args": { + "External id": 1416583,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534436407.028, "dur": 6.675, + "args": { + "External id": 1416584,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436410.008, "dur": 2.564, + "args": { + "External id": 1416585,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436430.792, "dur": 26.593, + "args": { + "External id": 1416586,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534436465.134, "dur": 5.673, + "args": { + "External id": 1416587,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534436466.621, "dur": 3.386, + "args": { + "External id": 1416588,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436468.913, "dur": 0.926, + "args": { + "External id": 1416589,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534436473.929, "dur": 46.102, + "args": { + "External id": 1416590,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534436475.133, "dur": 44.295, + "args": { + "External id": 1416591,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436523.848, "dur": 14.626, + "args": { + "External id": 1416592,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534436545.064, "dur": 6.793, + "args": { + "External id": 1416593,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436550.206, "dur": 0.611, + "args": { + "External id": 1416594,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534436555.851, "dur": 50.374, + "args": { + "External id": 1416595,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534436556.460, "dur": 3.949, + "args": { + "External id": 1416596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534436557.263, "dur": 2.552, + "args": { + "External id": 1416597,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436558.895, "dur": 0.771, + "args": { + "External id": 1416598,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534436561.208, "dur": 44.590, + "args": { + "External id": 1416599,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534436564.428, "dur": 40.793, + "args": { + "External id": 1416600,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534436610.728, "dur": 3.713, + "args": { + "External id": 1416601,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436612.677, "dur": 0.544, + "args": { + "External id": 1416602,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534436620.105, "dur": 1.643, + "args": { + "External id": 1416603,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534436629.640, "dur": 6.715, + "args": { + "External id": 1416604,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534436631.825, "dur": 4.250, + "args": { + "External id": 1416605,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534436724.132, "dur": 193.916, + "args": { + "External id": 1416606,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534436726.219, "dur": 4.730, + "args": { + "External id": 1416607,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534436732.673, "dur": 184.980, + "args": { + "External id": 1416608,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534436734.004, "dur": 0.469, + "args": { + "External id": 1416609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534436735.917, "dur": 20.980, + "args": { + "External id": 1416610,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534436758.806, "dur": 7.213, + "args": { + "External id": 1416611,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436765.366, "dur": 0.415, + "args": { + "External id": 1416612,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534436767.248, "dur": 24.494, + "args": { + "External id": 1416613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534436770.572, "dur": 1.195, + "args": { + "External id": 1416614,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534436772.948, "dur": 18.542, + "args": { + "External id": 1416615,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436775.649, "dur": 2.604, + "args": { + "External id": 1416616,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534436793.340, "dur": 21.507, + "args": { + "External id": 1416617,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436816.367, "dur": 14.068, + "args": { + "External id": 1416618,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534436833.086, "dur": 14.313, + "args": { + "External id": 1416619,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436848.674, "dur": 13.752, + "args": { + "External id": 1416620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534436864.510, "dur": 24.537, + "args": { + "External id": 1416621,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436866.806, "dur": 1.634, + "args": { + "External id": 1416622,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436872.287, "dur": 2.167, + "args": { + "External id": 1416623,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436890.790, "dur": 13.318, + "args": { + "External id": 1416624,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534436905.241, "dur": 11.371, + "args": { + "External id": 1416625,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534436924.749, "dur": 1.962, + "args": { + "External id": 1416626,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534436934.283, "dur": 3.522, + "args": { + "External id": 1416627,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534436936.352, "dur": 0.521, + "args": { + "External id": 1416628,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534436998.297, "dur": 48.297, + "args": { + "External id": 1416629,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534437051.605, "dur": 45.084, + "args": { + "External id": 1416630,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437093.620, "dur": 0.910, + "args": { + "External id": 1416631,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437098.349, "dur": 30.040, + "args": { + "External id": 1416632,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534437134.196, "dur": 6.133, + "args": { + "External id": 1416633,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534437135.729, "dur": 3.857, + "args": { + "External id": 1416634,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437138.104, "dur": 1.269, + "args": { + "External id": 1416635,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534437143.304, "dur": 46.767, + "args": { + "External id": 1416636,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534437144.369, "dur": 45.104, + "args": { + "External id": 1416637,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437196.270, "dur": 14.983, + "args": { + "External id": 1416638,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534437215.964, "dur": 24.466, + "args": { + "External id": 1416639,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534437218.675, "dur": 21.325, + "args": { + "External id": 1416640,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437224.022, "dur": 0.960, + "args": { + "External id": 1416641,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534437246.770, "dur": 27.486, + "args": { + "External id": 1416642,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534437248.862, "dur": 25.181, + "args": { + "External id": 1416643,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 19463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437253.822, "dur": 3.697, + "args": { + "External id": 1416644,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437258.690, "dur": 14.969, + "args": { + "External id": 1416645,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534437291.316, "dur": 5.470, + "args": { + "External id": 1416646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534437293.569, "dur": 2.937, + "args": { + "External id": 1416647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534437298.110, "dur": 1.449, + "args": { + "External id": 1416648,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534437299.022, "dur": 0.463, + "args": { + "External id": 1416649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437343.264, "dur": 22.538, + "args": { + "External id": 1416650,"Sequence number": 15109272, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 19470 + } + }, + { + "ph": "s", "id": 247, "pid": 2338710, "tid": 2338710, "ts": 6410534437343.264, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534437372.154, "dur": 6.581, + "args": { + "External id": 1416651,"Sequence number": 15109273, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 19471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437376.233, "dur": 1.150, + "args": { + "External id": 1416652,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410534437383.346, "dur": 6.076, + "args": { + "External id": 1416653,"Sequence number": 15109273, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "1"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 19473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437387.704, "dur": 0.507, + "args": { + "External id": 1416654,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534437390.746, "dur": 3.222, + "args": { + "External id": 1416655,"Sequence number": 15109273, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 19475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437392.864, "dur": 0.529, + "args": { + "External id": 1416656,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 19476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534437398.693, "dur": 8.243, + "args": { + "External id": 1416657,"Sequence number": 15109273, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19477 + } + }, + { + "ph": "s", "id": 246, "pid": 2338710, "tid": 2338710, "ts": 6410534437398.693, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437404.544, "dur": 0.948, + "args": { + "External id": 1416658,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534437408.086, "dur": 4.638, + "args": { + "External id": 1416659,"Sequence number": 15109274, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19479 + } + }, + { + "ph": "s", "id": 245, "pid": 2338710, "tid": 2338710, "ts": 6410534437408.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437411.504, "dur": 0.417, + "args": { + "External id": 1416660,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410534437428.848, "dur": 10.186, + "args": { + "External id": 1416661,"Sequence number": 15109275, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 19481 + } + }, + { + "ph": "s", "id": 244, "pid": 2338710, "tid": 2338710, "ts": 6410534437428.848, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437436.399, "dur": 1.051, + "args": { + "External id": 1416662,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534437440.789, "dur": 7.539, + "args": { + "External id": 1416663,"Sequence number": 15109276, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 19483 + } + }, + { + "ph": "s", "id": 243, "pid": 2338710, "tid": 2338710, "ts": 6410534437440.789, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437444.325, "dur": 3.039, + "args": { + "External id": 1416664,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 19484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410534437453.337, "dur": 32.617, + "args": { + "External id": 1416665,"Sequence number": 15109277, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410534437454.970, "dur": 30.778, + "args": { + "External id": 1416666,"Sequence number": 15109277, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534437457.686, "dur": 7.317, + "args": { + "External id": 1416667,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 19487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534437460.129, "dur": 4.278, + "args": { + "External id": 1416668,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437466.484, "dur": 18.856, + "args": { + "External id": 1416669,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 19489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534437512.142, "dur": 6.713, + "args": { + "External id": 1416670,"Sequence number": 15109277, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 19490 + } + }, + { + "ph": "s", "id": 242, "pid": 2338710, "tid": 2338710, "ts": 6410534437512.142, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534437523.516, "dur": 0.900, + "args": { + "External id": 1416671,"Sequence number": 15109278, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534437556.535, "dur": 46100.925, + "args": { + "External id": 1416672,"Sequence number": 15109278, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 19492 + } + }, + { + "ph": "s", "id": 241, "pid": 2338710, "tid": 2338710, "ts": 6410534437556.535, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410534437572.366, "dur": 26.063, + "args": { + "External id": 1416673,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410534437573.210, "dur": 25.031, + "args": { + "External id": 1416674,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534437574.684, "dur": 5.116, + "args": { + "External id": 1416675,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534437575.771, "dur": 3.598, + "args": { + "External id": 1416676,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437580.416, "dur": 17.334, + "args": { + "External id": 1416677,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 19497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534437614.916, "dur": 27.374, + "args": { + "External id": 1416678,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534437616.037, "dur": 5.980, + "args": { + "External id": 1416679,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437618.282, "dur": 3.462, + "args": { + "External id": 1416680,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437623.325, "dur": 18.758, + "args": { + "External id": 1416681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437627.563, "dur": 14.117, + "args": { + "External id": 1416682,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534437645.873, "dur": 20.004, + "args": { + "External id": 1416683,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534437646.942, "dur": 5.431, + "args": { + "External id": 1416684,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437648.755, "dur": 3.375, + "args": { + "External id": 1416685,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437653.084, "dur": 12.594, + "args": { + "External id": 1416686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437653.802, "dur": 11.470, + "args": { + "External id": 1416687,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 19507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410534437672.328, "dur": 21.602, + "args": { + "External id": 1416688,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534437675.867, "dur": 2.547, + "args": { + "External id": 1416689,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437679.058, "dur": 14.602, + "args": { + "External id": 1416690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 19510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437682.178, "dur": 11.145, + "args": { + "External id": 1416691,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410534437698.336, "dur": 23.867, + "args": { + "External id": 1416692,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534437725.316, "dur": 49.321, + "args": { + "External id": 1416693,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534437727.553, "dur": 46.687, + "args": { + "External id": 1416694,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437732.050, "dur": 0.994, + "args": { + "External id": 1416695,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534437734.557, "dur": 24.731, + "args": { + "External id": 1416696,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534437736.286, "dur": 22.795, + "args": { + "External id": 1416697,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 19517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534437740.195, "dur": 3.054, + "args": { + "External id": 1416698,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534437744.097, "dur": 14.590, + "args": { + "External id": 1416699,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 19519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410534437778.696, "dur": 40004.146, + "args": { + "External id": 1416700,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410534437780.263, "dur": 40000.303, + "args": { + "External id": 1416701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534477804.092, "dur": 10.554, + "args": { + "External id": 1416702,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534477810.389, "dur": 1.523, + "args": { + "External id": 1416703,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534477820.453, "dur": 139.521, + "args": { + "External id": 1416704,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534477840.586, "dur": 7.264, + "args": { + "External id": 1416705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534477843.341, "dur": 3.567, + "args": { + "External id": 1416706,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534477845.522, "dur": 1.098, + "args": { + "External id": 1416707,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534477851.424, "dur": 107.778, + "args": { + "External id": 1416708,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534477853.315, "dur": 104.821, + "args": { + "External id": 1416709,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534477964.889, "dur": 5.124, + "args": { + "External id": 1416710,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534477967.439, "dur": 0.833, + "args": { + "External id": 1416711,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534477979.971, "dur": 3.156, + "args": { + "External id": 1416712,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534477994.713, "dur": 10.197, + "args": { + "External id": 1416713,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534477999.300, "dur": 5.301, + "args": { + "External id": 1416714,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534478181.876, "dur": 212.937, + "args": { + "External id": 1416715,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534478186.413, "dur": 3.117, + "args": { + "External id": 1416716,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534478191.789, "dur": 202.468, + "args": { + "External id": 1416717,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534478193.472, "dur": 0.498, + "args": { + "External id": 1416718,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534478195.336, "dur": 32.688, + "args": { + "External id": 1416719,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534478230.483, "dur": 5.354, + "args": { + "External id": 1416720,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478234.591, "dur": 0.904, + "args": { + "External id": 1416721,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534478237.095, "dur": 28.345, + "args": { + "External id": 1416722,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534478240.756, "dur": 1.023, + "args": { + "External id": 1416723,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534478243.219, "dur": 21.898, + "args": { + "External id": 1416724,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478247.345, "dur": 3.576, + "args": { + "External id": 1416725,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534478267.276, "dur": 22.752, + "args": { + "External id": 1416726,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478292.262, "dur": 16.247, + "args": { + "External id": 1416727,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534478311.648, "dur": 14.571, + "args": { + "External id": 1416728,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478327.730, "dur": 13.199, + "args": { + "External id": 1416729,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534478342.988, "dur": 23.497, + "args": { + "External id": 1416730,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478345.576, "dur": 1.647, + "args": { + "External id": 1416731,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478352.294, "dur": 0.670, + "args": { + "External id": 1416732,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478368.451, "dur": 12.005, + "args": { + "External id": 1416733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478381.789, "dur": 11.090, + "args": { + "External id": 1416734,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534478403.137, "dur": 2.642, + "args": { + "External id": 1416735,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534478413.615, "dur": 17.848, + "args": { + "External id": 1416736,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478429.192, "dur": 0.804, + "args": { + "External id": 1416737,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534478515.199, "dur": 76.016, + "args": { + "External id": 1416738,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534478599.518, "dur": 7.208, + "args": { + "External id": 1416739,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478603.147, "dur": 0.816, + "args": { + "External id": 1416740,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478608.474, "dur": 27.934, + "args": { + "External id": 1416741,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534478645.406, "dur": 7.236, + "args": { + "External id": 1416742,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534478647.599, "dur": 4.162, + "args": { + "External id": 1416743,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478649.657, "dur": 1.799, + "args": { + "External id": 1416744,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534478658.662, "dur": 47.510, + "args": { + "External id": 1416745,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534478660.241, "dur": 45.332, + "args": { + "External id": 1416746,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478711.308, "dur": 16.880, + "args": { + "External id": 1416747,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534478735.083, "dur": 4.181, + "args": { + "External id": 1416748,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478737.792, "dur": 0.451, + "args": { + "External id": 1416749,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534478743.930, "dur": 51.055, + "args": { + "External id": 1416750,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534478744.894, "dur": 6.430, + "args": { + "External id": 1416751,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534478748.237, "dur": 2.468, + "args": { + "External id": 1416752,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478749.724, "dur": 0.792, + "args": { + "External id": 1416753,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534478752.128, "dur": 42.412, + "args": { + "External id": 1416754,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534478753.158, "dur": 40.750, + "args": { + "External id": 1416755,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534478800.559, "dur": 4.461, + "args": { + "External id": 1416756,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478803.090, "dur": 0.574, + "args": { + "External id": 1416757,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534478811.731, "dur": 2.376, + "args": { + "External id": 1416758,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534478824.650, "dur": 7.172, + "args": { + "External id": 1416759,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534478826.795, "dur": 4.742, + "args": { + "External id": 1416760,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534478931.997, "dur": 235.778, + "args": { + "External id": 1416761,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534478934.092, "dur": 1.979, + "args": { + "External id": 1416762,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534478939.431, "dur": 227.664, + "args": { + "External id": 1416763,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534478940.915, "dur": 0.547, + "args": { + "External id": 1416764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534478945.027, "dur": 21.262, + "args": { + "External id": 1416765,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534478968.299, "dur": 5.035, + "args": { + "External id": 1416766,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534478970.492, "dur": 2.592, + "args": { + "External id": 1416767,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534478974.137, "dur": 23.284, + "args": { + "External id": 1416768,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534478975.991, "dur": 1.326, + "args": { + "External id": 1416769,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534478978.599, "dur": 18.532, + "args": { + "External id": 1416770,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534478981.774, "dur": 2.150, + "args": { + "External id": 1416771,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534478999.286, "dur": 25.691, + "args": { + "External id": 1416772,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479026.638, "dur": 14.805, + "args": { + "External id": 1416773,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534479044.306, "dur": 50.952, + "args": { + "External id": 1416774,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479097.657, "dur": 14.374, + "args": { + "External id": 1416775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534479116.871, "dur": 23.260, + "args": { + "External id": 1416776,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479119.158, "dur": 2.246, + "args": { + "External id": 1416777,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479123.840, "dur": 2.316, + "args": { + "External id": 1416778,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479141.561, "dur": 12.223, + "args": { + "External id": 1416779,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479154.879, "dur": 10.898, + "args": { + "External id": 1416780,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534479175.950, "dur": 2.544, + "args": { + "External id": 1416781,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534479189.287, "dur": 4.331, + "args": { + "External id": 1416782,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479191.924, "dur": 0.622, + "args": { + "External id": 1416783,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534479271.131, "dur": 64.580, + "args": { + "External id": 1416784,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534479340.811, "dur": 4.799, + "args": { + "External id": 1416785,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479343.694, "dur": 0.662, + "args": { + "External id": 1416786,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479347.394, "dur": 28.203, + "args": { + "External id": 1416787,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534479380.171, "dur": 8.499, + "args": { + "External id": 1416788,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534479381.849, "dur": 6.066, + "args": { + "External id": 1416789,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479386.352, "dur": 1.392, + "args": { + "External id": 1416790,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534479391.666, "dur": 60.106, + "args": { + "External id": 1416791,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534479393.090, "dur": 57.682, + "args": { + "External id": 1416792,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479457.341, "dur": 16.456, + "args": { + "External id": 1416793,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534479481.139, "dur": 4.982, + "args": { + "External id": 1416794,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479484.097, "dur": 0.753, + "args": { + "External id": 1416795,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534479490.398, "dur": 50.919, + "args": { + "External id": 1416796,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534479493.666, "dur": 3.705, + "args": { + "External id": 1416797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534479494.518, "dur": 2.280, + "args": { + "External id": 1416798,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479496.125, "dur": 0.544, + "args": { + "External id": 1416799,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534479497.992, "dur": 42.920, + "args": { + "External id": 1416800,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534479499.034, "dur": 41.183, + "args": { + "External id": 1416801,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534479546.279, "dur": 3.947, + "args": { + "External id": 1416802,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479548.491, "dur": 0.570, + "args": { + "External id": 1416803,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534479558.478, "dur": 2.055, + "args": { + "External id": 1416804,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534479569.397, "dur": 6.364, + "args": { + "External id": 1416805,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534479571.492, "dur": 3.983, + "args": { + "External id": 1416806,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534479668.607, "dur": 192.804, + "args": { + "External id": 1416807,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534479671.924, "dur": 3.833, + "args": { + "External id": 1416808,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534479677.493, "dur": 183.458, + "args": { + "External id": 1416809,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534479681.068, "dur": 0.317, + "args": { + "External id": 1416810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534479682.590, "dur": 20.321, + "args": { + "External id": 1416811,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534479704.859, "dur": 4.650, + "args": { + "External id": 1416812,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479708.337, "dur": 0.935, + "args": { + "External id": 1416813,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534479710.262, "dur": 23.223, + "args": { + "External id": 1416814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534479711.555, "dur": 1.059, + "args": { + "External id": 1416815,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534479713.709, "dur": 19.457, + "args": { + "External id": 1416816,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479716.359, "dur": 3.259, + "args": { + "External id": 1416817,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534479734.964, "dur": 19.956, + "args": { + "External id": 1416818,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479756.354, "dur": 18.465, + "args": { + "External id": 1416819,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534479779.246, "dur": 14.933, + "args": { + "External id": 1416820,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479795.432, "dur": 13.579, + "args": { + "External id": 1416821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534479811.091, "dur": 20.997, + "args": { + "External id": 1416822,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479814.319, "dur": 1.518, + "args": { + "External id": 1416823,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479818.057, "dur": 0.690, + "args": { + "External id": 1416824,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479833.432, "dur": 11.367, + "args": { + "External id": 1416825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534479848.451, "dur": 11.335, + "args": { + "External id": 1416826,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534479867.473, "dur": 2.039, + "args": { + "External id": 1416827,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534479878.686, "dur": 3.796, + "args": { + "External id": 1416828,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534479881.361, "dur": 0.293, + "args": { + "External id": 1416829,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534479950.712, "dur": 80.186, + "args": { + "External id": 1416830,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534480035.707, "dur": 5.134, + "args": { + "External id": 1416831,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480038.777, "dur": 0.660, + "args": { + "External id": 1416832,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480042.294, "dur": 64.272, + "args": { + "External id": 1416833,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534480115.611, "dur": 6.080, + "args": { + "External id": 1416834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534480116.991, "dur": 3.889, + "args": { + "External id": 1416835,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480119.428, "dur": 1.260, + "args": { + "External id": 1416836,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534480125.046, "dur": 48.187, + "args": { + "External id": 1416837,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534480126.298, "dur": 46.375, + "args": { + "External id": 1416838,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480177.266, "dur": 15.508, + "args": { + "External id": 1416839,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534480199.826, "dur": 6.705, + "args": { + "External id": 1416840,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480204.667, "dur": 0.771, + "args": { + "External id": 1416841,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534480210.764, "dur": 47.576, + "args": { + "External id": 1416842,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534480211.904, "dur": 3.706, + "args": { + "External id": 1416843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534480213.106, "dur": 1.915, + "args": { + "External id": 1416844,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480214.541, "dur": 0.332, + "args": { + "External id": 1416845,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534480216.148, "dur": 41.719, + "args": { + "External id": 1416846,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534480219.390, "dur": 37.918, + "args": { + "External id": 1416847,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534480263.200, "dur": 4.016, + "args": { + "External id": 1416848,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480265.581, "dur": 0.316, + "args": { + "External id": 1416849,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534480273.428, "dur": 1.618, + "args": { + "External id": 1416850,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534480282.659, "dur": 7.613, + "args": { + "External id": 1416851,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534480285.096, "dur": 4.905, + "args": { + "External id": 1416852,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534480382.560, "dur": 205.243, + "args": { + "External id": 1416853,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534480386.441, "dur": 2.226, + "args": { + "External id": 1416854,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534480390.188, "dur": 197.135, + "args": { + "External id": 1416855,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534480391.339, "dur": 0.514, + "args": { + "External id": 1416856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534480393.764, "dur": 37.918, + "args": { + "External id": 1416857,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534480434.140, "dur": 4.777, + "args": { + "External id": 1416858,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480437.823, "dur": 0.841, + "args": { + "External id": 1416859,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534480439.855, "dur": 23.938, + "args": { + "External id": 1416860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534480441.335, "dur": 1.446, + "args": { + "External id": 1416861,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534480446.170, "dur": 17.330, + "args": { + "External id": 1416862,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480449.241, "dur": 2.463, + "args": { + "External id": 1416863,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534480465.062, "dur": 21.837, + "args": { + "External id": 1416864,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480488.782, "dur": 12.086, + "args": { + "External id": 1416865,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534480503.517, "dur": 13.108, + "args": { + "External id": 1416866,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480520.844, "dur": 12.270, + "args": { + "External id": 1416867,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534480535.358, "dur": 19.803, + "args": { + "External id": 1416868,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480537.579, "dur": 1.316, + "args": { + "External id": 1416869,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480541.088, "dur": 0.742, + "args": { + "External id": 1416870,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480558.622, "dur": 13.864, + "args": { + "External id": 1416871,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480573.514, "dur": 12.578, + "args": { + "External id": 1416872,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534480596.049, "dur": 2.188, + "args": { + "External id": 1416873,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534480607.416, "dur": 3.924, + "args": { + "External id": 1416874,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480610.131, "dur": 0.369, + "args": { + "External id": 1416875,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534480680.172, "dur": 56.146, + "args": { + "External id": 1416876,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534480741.407, "dur": 4.942, + "args": { + "External id": 1416877,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480744.178, "dur": 0.972, + "args": { + "External id": 1416878,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480750.221, "dur": 25.450, + "args": { + "External id": 1416879,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534480780.088, "dur": 6.771, + "args": { + "External id": 1416880,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534480781.593, "dur": 4.614, + "args": { + "External id": 1416881,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480783.730, "dur": 2.268, + "args": { + "External id": 1416882,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534480789.368, "dur": 42.287, + "args": { + "External id": 1416883,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534480790.554, "dur": 40.504, + "args": { + "External id": 1416884,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534480835.605, "dur": 15.739, + "args": { + "External id": 1416885,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534480860.213, "dur": 3.593, + "args": { + "External id": 1416886,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480862.301, "dur": 0.623, + "args": { + "External id": 1416887,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534480867.441, "dur": 46.503, + "args": { + "External id": 1416888,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534480868.551, "dur": 3.982, + "args": { + "External id": 1416889,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534480869.515, "dur": 2.424, + "args": { + "External id": 1416890,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480870.901, "dur": 0.869, + "args": { + "External id": 1416891,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534480875.277, "dur": 38.323, + "args": { + "External id": 1416892,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534480875.748, "dur": 37.452, + "args": { + "External id": 1416893,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534480917.808, "dur": 3.586, + "args": { + "External id": 1416894,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534480919.781, "dur": 0.493, + "args": { + "External id": 1416895,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534480926.999, "dur": 1.412, + "args": { + "External id": 1416896,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534480935.818, "dur": 9.127, + "args": { + "External id": 1416897,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534480940.112, "dur": 4.565, + "args": { + "External id": 1416898,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534481029.517, "dur": 227.059, + "args": { + "External id": 1416899,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534481031.861, "dur": 2.120, + "args": { + "External id": 1416900,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534481037.057, "dur": 218.983, + "args": { + "External id": 1416901,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534481038.269, "dur": 0.295, + "args": { + "External id": 1416902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534481039.985, "dur": 57.673, + "args": { + "External id": 1416903,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534481100.189, "dur": 5.069, + "args": { + "External id": 1416904,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481102.431, "dur": 2.529, + "args": { + "External id": 1416905,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534481106.228, "dur": 27.526, + "args": { + "External id": 1416906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534481109.520, "dur": 1.766, + "args": { + "External id": 1416907,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534481112.245, "dur": 21.237, + "args": { + "External id": 1416908,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481115.247, "dur": 3.137, + "args": { + "External id": 1416909,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534481135.090, "dur": 20.857, + "args": { + "External id": 1416910,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481157.360, "dur": 14.889, + "args": { + "External id": 1416911,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534481174.859, "dur": 13.686, + "args": { + "External id": 1416912,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481189.798, "dur": 13.904, + "args": { + "External id": 1416913,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534481205.535, "dur": 22.680, + "args": { + "External id": 1416914,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481207.827, "dur": 1.421, + "args": { + "External id": 1416915,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481213.102, "dur": 0.650, + "args": { + "External id": 1416916,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481229.775, "dur": 12.913, + "args": { + "External id": 1416917,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481243.902, "dur": 10.832, + "args": { + "External id": 1416918,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534481264.648, "dur": 2.014, + "args": { + "External id": 1416919,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534481275.355, "dur": 3.762, + "args": { + "External id": 1416920,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481277.884, "dur": 0.316, + "args": { + "External id": 1416921,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534481350.771, "dur": 60.406, + "args": { + "External id": 1416922,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534481434.380, "dur": 8.231, + "args": { + "External id": 1416923,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481437.952, "dur": 2.786, + "args": { + "External id": 1416924,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481444.359, "dur": 30.288, + "args": { + "External id": 1416925,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534481480.183, "dur": 5.375, + "args": { + "External id": 1416926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534481481.949, "dur": 2.987, + "args": { + "External id": 1416927,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481483.877, "dur": 0.851, + "args": { + "External id": 1416928,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534481490.857, "dur": 49.261, + "args": { + "External id": 1416929,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534481492.391, "dur": 47.136, + "args": { + "External id": 1416930,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481544.035, "dur": 16.067, + "args": { + "External id": 1416931,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534481566.576, "dur": 4.290, + "args": { + "External id": 1416932,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481569.354, "dur": 0.535, + "args": { + "External id": 1416933,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534481575.275, "dur": 51.852, + "args": { + "External id": 1416934,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534481576.290, "dur": 6.198, + "args": { + "External id": 1416935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534481579.678, "dur": 2.163, + "args": { + "External id": 1416936,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481580.951, "dur": 0.758, + "args": { + "External id": 1416937,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534481583.230, "dur": 43.405, + "args": { + "External id": 1416938,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534481584.116, "dur": 41.953, + "args": { + "External id": 1416939,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534481631.986, "dur": 3.527, + "args": { + "External id": 1416940,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481633.997, "dur": 0.319, + "args": { + "External id": 1416941,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534481641.320, "dur": 1.567, + "args": { + "External id": 1416942,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534481653.656, "dur": 6.343, + "args": { + "External id": 1416943,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534481655.551, "dur": 4.166, + "args": { + "External id": 1416944,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534481755.731, "dur": 191.473, + "args": { + "External id": 1416945,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534481757.860, "dur": 5.511, + "args": { + "External id": 1416946,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534481764.826, "dur": 181.734, + "args": { + "External id": 1416947,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534481766.004, "dur": 0.391, + "args": { + "External id": 1416948,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534481769.780, "dur": 22.687, + "args": { + "External id": 1416949,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534481794.037, "dur": 5.285, + "args": { + "External id": 1416950,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481798.455, "dur": 0.665, + "args": { + "External id": 1416951,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534481800.280, "dur": 21.663, + "args": { + "External id": 1416952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534481801.844, "dur": 1.193, + "args": { + "External id": 1416953,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534481804.087, "dur": 17.571, + "args": { + "External id": 1416954,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481806.330, "dur": 2.406, + "args": { + "External id": 1416955,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534481823.180, "dur": 21.397, + "args": { + "External id": 1416956,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481846.178, "dur": 13.204, + "args": { + "External id": 1416957,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534481861.847, "dur": 15.103, + "args": { + "External id": 1416958,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481878.442, "dur": 13.409, + "args": { + "External id": 1416959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534481895.332, "dur": 23.457, + "args": { + "External id": 1416960,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481899.358, "dur": 1.685, + "args": { + "External id": 1416961,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481903.111, "dur": 0.505, + "args": { + "External id": 1416962,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481920.125, "dur": 13.113, + "args": { + "External id": 1416963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534481934.085, "dur": 11.413, + "args": { + "External id": 1416964,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534481953.708, "dur": 1.402, + "args": { + "External id": 1416965,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534481963.180, "dur": 3.463, + "args": { + "External id": 1416966,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534481965.391, "dur": 0.508, + "args": { + "External id": 1416967,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534482030.557, "dur": 91.475, + "args": { + "External id": 1416968,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534482129.858, "dur": 6.253, + "args": { + "External id": 1416969,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482133.410, "dur": 1.005, + "args": { + "External id": 1416970,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482137.573, "dur": 26.728, + "args": { + "External id": 1416971,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534482169.584, "dur": 8.020, + "args": { + "External id": 1416972,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534482171.452, "dur": 5.384, + "args": { + "External id": 1416973,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482175.500, "dur": 1.132, + "args": { + "External id": 1416974,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534482180.625, "dur": 46.912, + "args": { + "External id": 1416975,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534482181.730, "dur": 45.307, + "args": { + "External id": 1416976,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482231.197, "dur": 16.718, + "args": { + "External id": 1416977,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534482254.360, "dur": 4.097, + "args": { + "External id": 1416978,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482257.036, "dur": 0.601, + "args": { + "External id": 1416979,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534482262.898, "dur": 46.381, + "args": { + "External id": 1416980,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534482265.907, "dur": 3.573, + "args": { + "External id": 1416981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534482266.645, "dur": 2.161, + "args": { + "External id": 1416982,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482268.047, "dur": 0.615, + "args": { + "External id": 1416983,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534482270.061, "dur": 38.723, + "args": { + "External id": 1416984,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534482270.680, "dur": 37.724, + "args": { + "External id": 1416985,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534482313.756, "dur": 5.991, + "args": { + "External id": 1416986,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482318.116, "dur": 0.480, + "args": { + "External id": 1416987,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534482327.276, "dur": 1.596, + "args": { + "External id": 1416988,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534482337.317, "dur": 6.953, + "args": { + "External id": 1416989,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534482339.404, "dur": 4.593, + "args": { + "External id": 1416990,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534482452.701, "dur": 185.261, + "args": { + "External id": 1416991,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534482455.117, "dur": 5.224, + "args": { + "External id": 1416992,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534482462.221, "dur": 175.370, + "args": { + "External id": 1416993,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534482466.231, "dur": 0.374, + "args": { + "External id": 1416994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534482467.897, "dur": 24.807, + "args": { + "External id": 1416995,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534482494.303, "dur": 2.908, + "args": { + "External id": 1416996,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482496.276, "dur": 0.709, + "args": { + "External id": 1416997,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534482498.103, "dur": 23.299, + "args": { + "External id": 1416998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534482499.309, "dur": 1.158, + "args": { + "External id": 1416999,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534482501.470, "dur": 19.641, + "args": { + "External id": 1417000,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482505.324, "dur": 2.785, + "args": { + "External id": 1417001,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534482522.832, "dur": 21.392, + "args": { + "External id": 1417002,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482545.973, "dur": 13.025, + "args": { + "External id": 1417003,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534482563.546, "dur": 12.922, + "args": { + "External id": 1417004,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482577.687, "dur": 12.179, + "args": { + "External id": 1417005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534482591.587, "dur": 18.824, + "args": { + "External id": 1417006,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482593.793, "dur": 1.538, + "args": { + "External id": 1417007,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482597.406, "dur": 0.514, + "args": { + "External id": 1417008,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482611.778, "dur": 12.302, + "args": { + "External id": 1417009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482627.491, "dur": 9.072, + "args": { + "External id": 1417010,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534482644.960, "dur": 2.116, + "args": { + "External id": 1417011,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534482655.822, "dur": 3.538, + "args": { + "External id": 1417012,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482658.093, "dur": 0.420, + "args": { + "External id": 1417013,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534482725.482, "dur": 53.596, + "args": { + "External id": 1417014,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534482783.980, "dur": 4.580, + "args": { + "External id": 1417015,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482786.800, "dur": 0.651, + "args": { + "External id": 1417016,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482790.055, "dur": 24.056, + "args": { + "External id": 1417017,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534482819.960, "dur": 4.649, + "args": { + "External id": 1417018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534482821.520, "dur": 2.402, + "args": { + "External id": 1417019,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482822.988, "dur": 0.785, + "args": { + "External id": 1417020,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534482827.547, "dur": 40.825, + "args": { + "External id": 1417021,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534482828.393, "dur": 39.379, + "args": { + "External id": 1417022,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534482872.161, "dur": 13.458, + "args": { + "External id": 1417023,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534482891.510, "dur": 5.951, + "args": { + "External id": 1417024,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482896.144, "dur": 0.484, + "args": { + "External id": 1417025,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534482901.228, "dur": 46.550, + "args": { + "External id": 1417026,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534482902.221, "dur": 4.308, + "args": { + "External id": 1417027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534482902.812, "dur": 3.179, + "args": { + "External id": 1417028,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482904.125, "dur": 1.676, + "args": { + "External id": 1417029,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534482907.055, "dur": 40.220, + "args": { + "External id": 1417030,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534482910.222, "dur": 36.545, + "args": { + "External id": 1417031,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534482952.118, "dur": 3.881, + "args": { + "External id": 1417032,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534482954.333, "dur": 0.512, + "args": { + "External id": 1417033,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534482960.948, "dur": 1.433, + "args": { + "External id": 1417034,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534482969.718, "dur": 5.554, + "args": { + "External id": 1417035,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534482971.493, "dur": 3.517, + "args": { + "External id": 1417036,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534483054.807, "dur": 218.406, + "args": { + "External id": 1417037,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534483091.527, "dur": 3.128, + "args": { + "External id": 1417038,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534483096.601, "dur": 176.165, + "args": { + "External id": 1417039,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534483097.838, "dur": 0.499, + "args": { + "External id": 1417040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534483100.984, "dur": 25.470, + "args": { + "External id": 1417041,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534483128.179, "dur": 3.097, + "args": { + "External id": 1417042,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483130.087, "dur": 0.971, + "args": { + "External id": 1417043,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534483132.072, "dur": 24.027, + "args": { + "External id": 1417044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534483133.399, "dur": 2.754, + "args": { + "External id": 1417045,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534483139.533, "dur": 16.316, + "args": { + "External id": 1417046,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483142.155, "dur": 2.230, + "args": { + "External id": 1417047,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534483157.426, "dur": 19.495, + "args": { + "External id": 1417048,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483178.412, "dur": 13.284, + "args": { + "External id": 1417049,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534483194.108, "dur": 13.608, + "args": { + "External id": 1417050,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483209.194, "dur": 11.335, + "args": { + "External id": 1417051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534483222.112, "dur": 21.733, + "args": { + "External id": 1417052,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483223.992, "dur": 1.202, + "args": { + "External id": 1417053,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483227.177, "dur": 0.719, + "args": { + "External id": 1417054,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483247.370, "dur": 11.308, + "args": { + "External id": 1417055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483259.665, "dur": 12.004, + "args": { + "External id": 1417056,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534483281.888, "dur": 2.186, + "args": { + "External id": 1417057,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534483293.181, "dur": 3.875, + "args": { + "External id": 1417058,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483295.743, "dur": 0.501, + "args": { + "External id": 1417059,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534483361.047, "dur": 68.952, + "args": { + "External id": 1417060,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534483436.755, "dur": 6.246, + "args": { + "External id": 1417061,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483440.607, "dur": 0.973, + "args": { + "External id": 1417062,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483446.540, "dur": 26.420, + "args": { + "External id": 1417063,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534483478.198, "dur": 6.831, + "args": { + "External id": 1417064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534483479.556, "dur": 4.809, + "args": { + "External id": 1417065,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483481.518, "dur": 2.641, + "args": { + "External id": 1417066,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534483487.950, "dur": 46.219, + "args": { + "External id": 1417067,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534483489.193, "dur": 44.380, + "args": { + "External id": 1417068,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483537.920, "dur": 14.344, + "args": { + "External id": 1417069,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534483559.549, "dur": 22.398, + "args": { + "External id": 1417070,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534483562.018, "dur": 19.558, + "args": { + "External id": 1417071,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483566.949, "dur": 0.706, + "args": { + "External id": 1417072,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534483587.189, "dur": 25.752, + "args": { + "External id": 1417073,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534483588.859, "dur": 23.874, + "args": { + "External id": 1417074,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 19894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483593.913, "dur": 3.693, + "args": { + "External id": 1417075,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483598.825, "dur": 13.402, + "args": { + "External id": 1417076,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534483624.998, "dur": 7.037, + "args": { + "External id": 1417077,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534483629.008, "dur": 2.685, + "args": { + "External id": 1417078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534483633.029, "dur": 1.376, + "args": { + "External id": 1417079,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534483633.836, "dur": 0.498, + "args": { + "External id": 1417080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483675.220, "dur": 21.599, + "args": { + "External id": 1417081,"Sequence number": 15109279, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 19901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483698.676, "dur": 13.785, + "args": { + "External id": 1417082,"Sequence number": 15109280, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 19902 + } + }, + { + "ph": "s", "id": 240, "pid": 2338710, "tid": 2338710, "ts": 6410534483698.676, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534483718.168, "dur": 6.349, + "args": { + "External id": 1417083,"Sequence number": 15109281, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 19903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483721.789, "dur": 1.262, + "args": { + "External id": 1417084,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410534483726.973, "dur": 8.523, + "args": { + "External id": 1417085,"Sequence number": 15109281, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 19905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483733.713, "dur": 0.436, + "args": { + "External id": 1417086,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534483736.734, "dur": 2.342, + "args": { + "External id": 1417087,"Sequence number": 15109281, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 19907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483738.129, "dur": 0.377, + "args": { + "External id": 1417088,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 19908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534483743.553, "dur": 6.369, + "args": { + "External id": 1417089,"Sequence number": 15109281, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19909 + } + }, + { + "ph": "s", "id": 239, "pid": 2338710, "tid": 2338710, "ts": 6410534483743.553, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483747.710, "dur": 0.852, + "args": { + "External id": 1417090,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534483752.815, "dur": 5.225, + "args": { + "External id": 1417091,"Sequence number": 15109282, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19911 + } + }, + { + "ph": "s", "id": 238, "pid": 2338710, "tid": 2338710, "ts": 6410534483752.815, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483756.747, "dur": 0.453, + "args": { + "External id": 1417092,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410534483758.927, "dur": 4.786, + "args": { + "External id": 1417093,"Sequence number": 15109283, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 19913 + } + }, + { + "ph": "s", "id": 237, "pid": 2338710, "tid": 2338710, "ts": 6410534483758.927, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483762.239, "dur": 0.634, + "args": { + "External id": 1417094,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534483764.753, "dur": 7.029, + "args": { + "External id": 1417095,"Sequence number": 15109284, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 19915 + } + }, + { + "ph": "s", "id": 236, "pid": 2338710, "tid": 2338710, "ts": 6410534483764.753, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483768.039, "dur": 2.965, + "args": { + "External id": 1417096,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 19916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410534483775.410, "dur": 32.730, + "args": { + "External id": 1417097,"Sequence number": 15109285, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410534483778.956, "dur": 28.978, + "args": { + "External id": 1417098,"Sequence number": 15109285, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534483781.463, "dur": 6.202, + "args": { + "External id": 1417099,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 19919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534483783.754, "dur": 3.390, + "args": { + "External id": 1417100,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483788.499, "dur": 18.986, + "args": { + "External id": 1417101,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 19921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534483833.380, "dur": 4.096, + "args": { + "External id": 1417102,"Sequence number": 15109285, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 19922 + } + }, + { + "ph": "s", "id": 235, "pid": 2338710, "tid": 2338710, "ts": 6410534483833.380, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534483839.969, "dur": 1.025, + "args": { + "External id": 1417103,"Sequence number": 15109286, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534483876.074, "dur": 46534.217, + "args": { + "External id": 1417104,"Sequence number": 15109286, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 19924 + } + }, + { + "ph": "s", "id": 234, "pid": 2338710, "tid": 2338710, "ts": 6410534483876.074, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410534483891.480, "dur": 29.883, + "args": { + "External id": 1417105,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410534483897.289, "dur": 23.893, + "args": { + "External id": 1417106,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534483899.005, "dur": 4.300, + "args": { + "External id": 1417107,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534483900.237, "dur": 2.743, + "args": { + "External id": 1417108,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483904.400, "dur": 16.374, + "args": { + "External id": 1417109,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 19929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534483938.058, "dur": 25.967, + "args": { + "External id": 1417110,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534483939.224, "dur": 5.862, + "args": { + "External id": 1417111,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483941.353, "dur": 3.449, + "args": { + "External id": 1417112,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483946.264, "dur": 17.554, + "args": { + "External id": 1417113,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483950.555, "dur": 12.835, + "args": { + "External id": 1417114,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534483967.162, "dur": 19.305, + "args": { + "External id": 1417115,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534483968.127, "dur": 4.045, + "args": { + "External id": 1417116,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534483969.292, "dur": 2.628, + "args": { + "External id": 1417117,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483972.720, "dur": 13.554, + "args": { + "External id": 1417118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483973.380, "dur": 12.565, + "args": { + "External id": 1417119,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 19939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410534483993.129, "dur": 19.836, + "args": { + "External id": 1417120,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534483994.851, "dur": 3.175, + "args": { + "External id": 1417121,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534483998.665, "dur": 14.029, + "args": { + "External id": 1417122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 19942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534484002.112, "dur": 10.240, + "args": { + "External id": 1417123,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410534484017.978, "dur": 24.208, + "args": { + "External id": 1417124,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534484044.967, "dur": 90.985, + "args": { + "External id": 1417125,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534484047.081, "dur": 88.311, + "args": { + "External id": 1417126,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534484051.489, "dur": 0.766, + "args": { + "External id": 1417127,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534484053.472, "dur": 65.715, + "args": { + "External id": 1417128,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534484094.456, "dur": 24.426, + "args": { + "External id": 1417129,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 19949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534484097.958, "dur": 3.995, + "args": { + "External id": 1417130,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534484103.167, "dur": 15.386, + "args": { + "External id": 1417131,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 19951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410534484142.654, "dur": 40463.443, + "args": { + "External id": 1417132,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410534484144.176, "dur": 40460.497, + "args": { + "External id": 1417133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534524620.365, "dur": 7.990, + "args": { + "External id": 1417134,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534524624.946, "dur": 1.419, + "args": { + "External id": 1417135,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534524633.899, "dur": 106.359, + "args": { + "External id": 1417136,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534524635.506, "dur": 5.898, + "args": { + "External id": 1417137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534524637.547, "dur": 2.946, + "args": { + "External id": 1417138,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534524639.477, "dur": 0.709, + "args": { + "External id": 1417139,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534524645.291, "dur": 94.157, + "args": { + "External id": 1417140,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534524647.028, "dur": 91.314, + "args": { + "External id": 1417141,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534524744.048, "dur": 4.965, + "args": { + "External id": 1417142,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534524746.759, "dur": 0.734, + "args": { + "External id": 1417143,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534524756.798, "dur": 2.630, + "args": { + "External id": 1417144,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534524769.623, "dur": 8.879, + "args": { + "External id": 1417145,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534524774.153, "dur": 4.027, + "args": { + "External id": 1417146,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534524916.667, "dur": 243.360, + "args": { + "External id": 1417147,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534524919.354, "dur": 3.527, + "args": { + "External id": 1417148,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534524924.900, "dur": 234.442, + "args": { + "External id": 1417149,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534524926.524, "dur": 0.596, + "args": { + "External id": 1417150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534524928.492, "dur": 25.269, + "args": { + "External id": 1417151,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534524955.840, "dur": 5.273, + "args": { + "External id": 1417152,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534524960.208, "dur": 0.645, + "args": { + "External id": 1417153,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534524962.387, "dur": 32.456, + "args": { + "External id": 1417154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534524969.693, "dur": 1.370, + "args": { + "External id": 1417155,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534524972.504, "dur": 22.055, + "args": { + "External id": 1417156,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534524978.561, "dur": 3.220, + "args": { + "External id": 1417157,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534524996.799, "dur": 22.809, + "args": { + "External id": 1417158,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525021.536, "dur": 14.352, + "args": { + "External id": 1417159,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534525038.814, "dur": 44.695, + "args": { + "External id": 1417160,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525086.122, "dur": 15.025, + "args": { + "External id": 1417161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534525103.778, "dur": 26.222, + "args": { + "External id": 1417162,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525108.165, "dur": 1.937, + "args": { + "External id": 1417163,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525114.531, "dur": 0.890, + "args": { + "External id": 1417164,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525131.821, "dur": 12.517, + "args": { + "External id": 1417165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525145.782, "dur": 12.108, + "args": { + "External id": 1417166,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534525168.734, "dur": 2.540, + "args": { + "External id": 1417167,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534525178.701, "dur": 4.583, + "args": { + "External id": 1417168,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525181.774, "dur": 0.534, + "args": { + "External id": 1417169,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534525264.749, "dur": 75.182, + "args": { + "External id": 1417170,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534525348.062, "dur": 6.372, + "args": { + "External id": 1417171,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525351.012, "dur": 0.671, + "args": { + "External id": 1417172,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525356.042, "dur": 30.458, + "args": { + "External id": 1417173,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534525392.250, "dur": 6.783, + "args": { + "External id": 1417174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534525394.224, "dur": 4.078, + "args": { + "External id": 1417175,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525396.278, "dur": 1.790, + "args": { + "External id": 1417176,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534525404.850, "dur": 66.093, + "args": { + "External id": 1417177,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534525406.197, "dur": 63.738, + "args": { + "External id": 1417178,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525476.673, "dur": 17.322, + "args": { + "External id": 1417179,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534525501.247, "dur": 4.826, + "args": { + "External id": 1417180,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525504.009, "dur": 0.844, + "args": { + "External id": 1417181,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534525510.810, "dur": 53.589, + "args": { + "External id": 1417182,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534525511.809, "dur": 6.746, + "args": { + "External id": 1417183,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534525515.160, "dur": 2.763, + "args": { + "External id": 1417184,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525516.937, "dur": 0.860, + "args": { + "External id": 1417185,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534525519.220, "dur": 44.668, + "args": { + "External id": 1417186,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534525520.115, "dur": 43.176, + "args": { + "External id": 1417187,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534525568.491, "dur": 3.857, + "args": { + "External id": 1417188,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525570.818, "dur": 0.357, + "args": { + "External id": 1417189,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534525581.385, "dur": 1.757, + "args": { + "External id": 1417190,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534525591.907, "dur": 7.028, + "args": { + "External id": 1417191,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534525594.220, "dur": 4.428, + "args": { + "External id": 1417192,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534525699.209, "dur": 183.597, + "args": { + "External id": 1417193,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534525703.274, "dur": 2.310, + "args": { + "External id": 1417194,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534525707.651, "dur": 174.558, + "args": { + "External id": 1417195,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534525711.164, "dur": 0.646, + "args": { + "External id": 1417196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534525713.380, "dur": 20.378, + "args": { + "External id": 1417197,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534525735.418, "dur": 4.970, + "args": { + "External id": 1417198,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525739.178, "dur": 0.969, + "args": { + "External id": 1417199,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534525741.357, "dur": 21.789, + "args": { + "External id": 1417200,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534525742.460, "dur": 1.258, + "args": { + "External id": 1417201,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534525744.993, "dur": 17.879, + "args": { + "External id": 1417202,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525748.109, "dur": 2.535, + "args": { + "External id": 1417203,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534525764.669, "dur": 21.678, + "args": { + "External id": 1417204,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525788.191, "dur": 15.335, + "args": { + "External id": 1417205,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534525808.655, "dur": 12.361, + "args": { + "External id": 1417206,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525822.449, "dur": 11.974, + "args": { + "External id": 1417207,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534525836.273, "dur": 20.064, + "args": { + "External id": 1417208,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525838.782, "dur": 2.056, + "args": { + "External id": 1417209,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525842.858, "dur": 0.658, + "args": { + "External id": 1417210,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525858.029, "dur": 11.346, + "args": { + "External id": 1417211,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534525870.636, "dur": 10.643, + "args": { + "External id": 1417212,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534525892.036, "dur": 1.689, + "args": { + "External id": 1417213,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534525903.196, "dur": 3.624, + "args": { + "External id": 1417214,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534525905.511, "dur": 0.440, + "args": { + "External id": 1417215,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534525974.718, "dur": 53.576, + "args": { + "External id": 1417216,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534526088.676, "dur": 8.600, + "args": { + "External id": 1417217,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526094.331, "dur": 0.999, + "args": { + "External id": 1417218,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526099.004, "dur": 30.032, + "args": { + "External id": 1417219,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534526137.319, "dur": 7.858, + "args": { + "External id": 1417220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534526138.693, "dur": 5.763, + "args": { + "External id": 1417221,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526142.374, "dur": 1.799, + "args": { + "External id": 1417222,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534526148.596, "dur": 49.074, + "args": { + "External id": 1417223,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534526149.803, "dur": 46.988, + "args": { + "External id": 1417224,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526201.680, "dur": 16.239, + "args": { + "External id": 1417225,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534526224.722, "dur": 6.111, + "args": { + "External id": 1417226,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526229.263, "dur": 0.620, + "args": { + "External id": 1417227,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534526235.012, "dur": 47.097, + "args": { + "External id": 1417228,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534526235.627, "dur": 3.771, + "args": { + "External id": 1417229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534526236.764, "dur": 2.079, + "args": { + "External id": 1417230,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526238.098, "dur": 0.592, + "args": { + "External id": 1417231,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534526240.181, "dur": 41.543, + "args": { + "External id": 1417232,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534526242.801, "dur": 38.219, + "args": { + "External id": 1417233,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534526286.673, "dur": 3.517, + "args": { + "External id": 1417234,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526288.658, "dur": 0.367, + "args": { + "External id": 1417235,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534526296.490, "dur": 1.553, + "args": { + "External id": 1417236,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534526306.850, "dur": 9.389, + "args": { + "External id": 1417237,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534526309.191, "dur": 6.757, + "args": { + "External id": 1417238,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534526413.447, "dur": 209.629, + "args": { + "External id": 1417239,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534526431.451, "dur": 3.106, + "args": { + "External id": 1417240,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534526438.243, "dur": 184.270, + "args": { + "External id": 1417241,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534526439.614, "dur": 0.274, + "args": { + "External id": 1417242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534526441.260, "dur": 23.384, + "args": { + "External id": 1417243,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534526466.217, "dur": 4.750, + "args": { + "External id": 1417244,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526469.003, "dur": 1.700, + "args": { + "External id": 1417245,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534526471.893, "dur": 23.399, + "args": { + "External id": 1417246,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534526473.320, "dur": 1.020, + "args": { + "External id": 1417247,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534526475.388, "dur": 19.639, + "args": { + "External id": 1417248,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526480.504, "dur": 2.934, + "args": { + "External id": 1417249,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534526496.629, "dur": 20.482, + "args": { + "External id": 1417250,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526518.758, "dur": 17.458, + "args": { + "External id": 1417251,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534526538.936, "dur": 15.075, + "args": { + "External id": 1417252,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526555.874, "dur": 13.543, + "args": { + "External id": 1417253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534526571.295, "dur": 20.949, + "args": { + "External id": 1417254,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526573.409, "dur": 1.315, + "args": { + "External id": 1417255,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526576.925, "dur": 0.453, + "args": { + "External id": 1417256,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526595.699, "dur": 12.998, + "args": { + "External id": 1417257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526609.671, "dur": 12.012, + "args": { + "External id": 1417258,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534526630.737, "dur": 2.228, + "args": { + "External id": 1417259,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534526642.516, "dur": 3.897, + "args": { + "External id": 1417260,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526645.280, "dur": 0.349, + "args": { + "External id": 1417261,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534526725.193, "dur": 85.558, + "args": { + "External id": 1417262,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534526815.624, "dur": 8.203, + "args": { + "External id": 1417263,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526820.531, "dur": 2.012, + "args": { + "External id": 1417264,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526825.283, "dur": 29.057, + "args": { + "External id": 1417265,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534526858.775, "dur": 5.230, + "args": { + "External id": 1417266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534526860.276, "dur": 3.058, + "args": { + "External id": 1417267,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526862.227, "dur": 0.924, + "args": { + "External id": 1417268,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534526866.691, "dur": 42.527, + "args": { + "External id": 1417269,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534526867.786, "dur": 40.941, + "args": { + "External id": 1417270,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534526915.180, "dur": 13.798, + "args": { + "External id": 1417271,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534526934.655, "dur": 4.172, + "args": { + "External id": 1417272,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526937.336, "dur": 0.706, + "args": { + "External id": 1417273,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534526942.811, "dur": 46.027, + "args": { + "External id": 1417274,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534526943.593, "dur": 5.978, + "args": { + "External id": 1417275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534526944.283, "dur": 4.715, + "args": { + "External id": 1417276,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526948.501, "dur": 0.367, + "args": { + "External id": 1417277,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534526950.093, "dur": 38.425, + "args": { + "External id": 1417278,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534526950.564, "dur": 37.286, + "args": { + "External id": 1417279,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534526992.729, "dur": 3.741, + "args": { + "External id": 1417280,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534526994.596, "dur": 0.669, + "args": { + "External id": 1417281,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534527001.266, "dur": 1.438, + "args": { + "External id": 1417282,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534527011.945, "dur": 8.045, + "args": { + "External id": 1417283,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534527014.336, "dur": 5.430, + "args": { + "External id": 1417284,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534527144.106, "dur": 188.105, + "args": { + "External id": 1417285,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534527146.678, "dur": 3.852, + "args": { + "External id": 1417286,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534527152.197, "dur": 179.403, + "args": { + "External id": 1417287,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534527153.345, "dur": 0.537, + "args": { + "External id": 1417288,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534527155.145, "dur": 22.460, + "args": { + "External id": 1417289,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534527181.721, "dur": 6.075, + "args": { + "External id": 1417290,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527186.630, "dur": 0.909, + "args": { + "External id": 1417291,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534527188.601, "dur": 19.668, + "args": { + "External id": 1417292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534527189.614, "dur": 1.033, + "args": { + "External id": 1417293,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534527191.725, "dur": 16.253, + "args": { + "External id": 1417294,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527194.547, "dur": 2.431, + "args": { + "External id": 1417295,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534527209.465, "dur": 19.988, + "args": { + "External id": 1417296,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527231.017, "dur": 15.301, + "args": { + "External id": 1417297,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534527248.707, "dur": 13.196, + "args": { + "External id": 1417298,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527263.249, "dur": 13.230, + "args": { + "External id": 1417299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534527278.145, "dur": 25.247, + "args": { + "External id": 1417300,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527282.972, "dur": 1.360, + "args": { + "External id": 1417301,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527286.116, "dur": 2.492, + "args": { + "External id": 1417302,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527304.949, "dur": 13.433, + "args": { + "External id": 1417303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527319.354, "dur": 11.275, + "args": { + "External id": 1417304,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534527339.023, "dur": 2.355, + "args": { + "External id": 1417305,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534527350.219, "dur": 3.714, + "args": { + "External id": 1417306,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527352.807, "dur": 0.393, + "args": { + "External id": 1417307,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534527436.171, "dur": 61.569, + "args": { + "External id": 1417308,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534527505.810, "dur": 6.074, + "args": { + "External id": 1417309,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527509.462, "dur": 0.823, + "args": { + "External id": 1417310,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527513.213, "dur": 26.527, + "args": { + "External id": 1417311,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534527544.936, "dur": 5.636, + "args": { + "External id": 1417312,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534527546.323, "dur": 3.464, + "args": { + "External id": 1417313,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527548.465, "dur": 1.124, + "args": { + "External id": 1417314,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534527555.559, "dur": 43.355, + "args": { + "External id": 1417315,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534527556.473, "dur": 41.843, + "args": { + "External id": 1417316,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527602.502, "dur": 16.516, + "args": { + "External id": 1417317,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534527625.086, "dur": 3.507, + "args": { + "External id": 1417318,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527627.163, "dur": 0.589, + "args": { + "External id": 1417319,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534527632.214, "dur": 48.795, + "args": { + "External id": 1417320,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534527633.025, "dur": 7.326, + "args": { + "External id": 1417321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534527636.695, "dur": 3.088, + "args": { + "External id": 1417322,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527638.724, "dur": 0.929, + "args": { + "External id": 1417323,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534527641.189, "dur": 39.397, + "args": { + "External id": 1417324,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534527641.771, "dur": 38.219, + "args": { + "External id": 1417325,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534527684.933, "dur": 4.080, + "args": { + "External id": 1417326,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527687.107, "dur": 0.740, + "args": { + "External id": 1417327,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534527694.629, "dur": 1.640, + "args": { + "External id": 1417328,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534527706.243, "dur": 6.453, + "args": { + "External id": 1417329,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534527708.263, "dur": 4.132, + "args": { + "External id": 1417330,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534527800.413, "dur": 199.795, + "args": { + "External id": 1417331,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534527804.747, "dur": 1.791, + "args": { + "External id": 1417332,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534527808.280, "dur": 191.430, + "args": { + "External id": 1417333,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534527809.627, "dur": 0.324, + "args": { + "External id": 1417334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534527810.717, "dur": 21.542, + "args": { + "External id": 1417335,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534527836.336, "dur": 4.687, + "args": { + "External id": 1417336,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527839.911, "dur": 0.903, + "args": { + "External id": 1417337,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534527841.725, "dur": 22.559, + "args": { + "External id": 1417338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534527843.007, "dur": 1.092, + "args": { + "External id": 1417339,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534527845.368, "dur": 18.588, + "args": { + "External id": 1417340,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527847.715, "dur": 3.084, + "args": { + "External id": 1417341,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534527865.440, "dur": 21.809, + "args": { + "External id": 1417342,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527888.840, "dur": 16.526, + "args": { + "External id": 1417343,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534527915.499, "dur": 16.037, + "args": { + "External id": 1417344,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527932.885, "dur": 13.047, + "args": { + "External id": 1417345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534527950.136, "dur": 20.739, + "args": { + "External id": 1417346,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527952.280, "dur": 1.142, + "args": { + "External id": 1417347,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534527955.477, "dur": 0.526, + "args": { + "External id": 1417348,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527972.434, "dur": 13.145, + "args": { + "External id": 1417349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534527986.427, "dur": 12.254, + "args": { + "External id": 1417350,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534528007.135, "dur": 1.724, + "args": { + "External id": 1417351,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534528019.452, "dur": 3.773, + "args": { + "External id": 1417352,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528021.864, "dur": 0.468, + "args": { + "External id": 1417353,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534528128.767, "dur": 65.277, + "args": { + "External id": 1417354,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534528199.528, "dur": 6.201, + "args": { + "External id": 1417355,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528203.174, "dur": 1.037, + "args": { + "External id": 1417356,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528207.327, "dur": 30.678, + "args": { + "External id": 1417357,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534528243.151, "dur": 8.966, + "args": { + "External id": 1417358,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534528244.825, "dur": 6.558, + "args": { + "External id": 1417359,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528248.921, "dur": 2.206, + "args": { + "External id": 1417360,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534528254.989, "dur": 43.956, + "args": { + "External id": 1417361,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534528256.101, "dur": 42.221, + "args": { + "External id": 1417362,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528302.449, "dur": 23.235, + "args": { + "External id": 1417363,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534528331.717, "dur": 3.593, + "args": { + "External id": 1417364,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528333.833, "dur": 0.587, + "args": { + "External id": 1417365,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534528344.151, "dur": 46.207, + "args": { + "External id": 1417366,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534528345.127, "dur": 3.556, + "args": { + "External id": 1417367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534528345.967, "dur": 2.147, + "args": { + "External id": 1417368,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528347.443, "dur": 0.524, + "args": { + "External id": 1417369,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534528349.342, "dur": 40.623, + "args": { + "External id": 1417370,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534528350.089, "dur": 39.189, + "args": { + "External id": 1417371,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534528396.759, "dur": 3.842, + "args": { + "External id": 1417372,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528398.935, "dur": 0.532, + "args": { + "External id": 1417373,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534528406.015, "dur": 1.543, + "args": { + "External id": 1417374,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534528432.247, "dur": 11.094, + "args": { + "External id": 1417375,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534528434.314, "dur": 8.507, + "args": { + "External id": 1417376,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534528539.928, "dur": 189.958, + "args": { + "External id": 1417377,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534528542.189, "dur": 1.908, + "args": { + "External id": 1417378,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534528546.285, "dur": 183.049, + "args": { + "External id": 1417379,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534528548.030, "dur": 0.334, + "args": { + "External id": 1417380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534528549.361, "dur": 24.666, + "args": { + "External id": 1417381,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534528575.559, "dur": 3.040, + "args": { + "External id": 1417382,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528577.529, "dur": 0.791, + "args": { + "External id": 1417383,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534528579.321, "dur": 25.991, + "args": { + "External id": 1417384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534528580.599, "dur": 1.542, + "args": { + "External id": 1417385,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534528583.168, "dur": 21.836, + "args": { + "External id": 1417386,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528589.414, "dur": 2.549, + "args": { + "External id": 1417387,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534528606.729, "dur": 21.529, + "args": { + "External id": 1417388,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528629.957, "dur": 15.004, + "args": { + "External id": 1417389,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534528647.923, "dur": 12.971, + "args": { + "External id": 1417390,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528662.225, "dur": 15.263, + "args": { + "External id": 1417391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534528679.338, "dur": 20.978, + "args": { + "External id": 1417392,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528681.611, "dur": 1.877, + "args": { + "External id": 1417393,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528685.465, "dur": 0.698, + "args": { + "External id": 1417394,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528704.293, "dur": 11.607, + "args": { + "External id": 1417395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528717.074, "dur": 11.022, + "args": { + "External id": 1417396,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534528736.417, "dur": 1.936, + "args": { + "External id": 1417397,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534528746.952, "dur": 3.464, + "args": { + "External id": 1417398,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528749.241, "dur": 0.425, + "args": { + "External id": 1417399,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534528811.720, "dur": 55.460, + "args": { + "External id": 1417400,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534528872.088, "dur": 4.864, + "args": { + "External id": 1417401,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528875.165, "dur": 0.709, + "args": { + "External id": 1417402,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528878.443, "dur": 24.379, + "args": { + "External id": 1417403,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534528909.758, "dur": 5.395, + "args": { + "External id": 1417404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534528911.518, "dur": 2.955, + "args": { + "External id": 1417405,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528913.325, "dur": 0.967, + "args": { + "External id": 1417406,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534528917.689, "dur": 41.265, + "args": { + "External id": 1417407,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534528918.535, "dur": 39.558, + "args": { + "External id": 1417408,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534528963.105, "dur": 13.854, + "args": { + "External id": 1417409,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534528982.378, "dur": 6.317, + "args": { + "External id": 1417410,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528987.119, "dur": 0.661, + "args": { + "External id": 1417411,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534528992.532, "dur": 46.229, + "args": { + "External id": 1417412,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534528993.268, "dur": 4.765, + "args": { + "External id": 1417413,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534528994.039, "dur": 3.396, + "args": { + "External id": 1417414,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534528995.281, "dur": 1.957, + "args": { + "External id": 1417415,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534528998.597, "dur": 39.767, + "args": { + "External id": 1417416,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534529001.322, "dur": 36.280, + "args": { + "External id": 1417417,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534529042.601, "dur": 5.571, + "args": { + "External id": 1417418,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529044.830, "dur": 2.180, + "args": { + "External id": 1417419,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534529053.412, "dur": 1.491, + "args": { + "External id": 1417420,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534529098.381, "dur": 7.658, + "args": { + "External id": 1417421,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534529100.577, "dur": 4.900, + "args": { + "External id": 1417422,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534529195.763, "dur": 178.853, + "args": { + "External id": 1417423,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534529198.448, "dur": 1.639, + "args": { + "External id": 1417424,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534529201.830, "dur": 172.204, + "args": { + "External id": 1417425,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534529203.152, "dur": 0.471, + "args": { + "External id": 1417426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534529206.987, "dur": 20.309, + "args": { + "External id": 1417427,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534529229.286, "dur": 2.961, + "args": { + "External id": 1417428,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529231.270, "dur": 0.758, + "args": { + "External id": 1417429,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534529233.041, "dur": 24.560, + "args": { + "External id": 1417430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534529234.426, "dur": 2.414, + "args": { + "External id": 1417431,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534529237.811, "dur": 19.484, + "args": { + "External id": 1417432,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529242.521, "dur": 3.008, + "args": { + "External id": 1417433,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534529259.052, "dur": 20.396, + "args": { + "External id": 1417434,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529281.014, "dur": 12.814, + "args": { + "External id": 1417435,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534529296.245, "dur": 13.058, + "args": { + "External id": 1417436,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529310.747, "dur": 11.516, + "args": { + "External id": 1417437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534529324.136, "dur": 20.180, + "args": { + "External id": 1417438,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529326.348, "dur": 1.266, + "args": { + "External id": 1417439,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529329.463, "dur": 0.620, + "args": { + "External id": 1417440,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529347.718, "dur": 12.409, + "args": { + "External id": 1417441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529361.129, "dur": 11.993, + "args": { + "External id": 1417442,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534529380.834, "dur": 1.937, + "args": { + "External id": 1417443,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534529391.823, "dur": 3.820, + "args": { + "External id": 1417444,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529394.371, "dur": 0.319, + "args": { + "External id": 1417445,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534529474.389, "dur": 60.901, + "args": { + "External id": 1417446,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534529540.621, "dur": 8.428, + "args": { + "External id": 1417447,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529546.628, "dur": 0.888, + "args": { + "External id": 1417448,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529550.367, "dur": 27.261, + "args": { + "External id": 1417449,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534529582.537, "dur": 7.146, + "args": { + "External id": 1417450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534529584.241, "dur": 4.738, + "args": { + "External id": 1417451,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529586.009, "dur": 2.797, + "args": { + "External id": 1417452,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534529592.235, "dur": 41.481, + "args": { + "External id": 1417453,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534529593.216, "dur": 39.898, + "args": { + "External id": 1417454,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529639.659, "dur": 14.977, + "args": { + "External id": 1417455,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534529660.444, "dur": 3.884, + "args": { + "External id": 1417456,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529662.685, "dur": 0.671, + "args": { + "External id": 1417457,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534529668.398, "dur": 45.703, + "args": { + "External id": 1417458,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534529669.154, "dur": 5.794, + "args": { + "External id": 1417459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534529670.001, "dur": 4.437, + "args": { + "External id": 1417460,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529673.565, "dur": 0.754, + "args": { + "External id": 1417461,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534529675.461, "dur": 38.309, + "args": { + "External id": 1417462,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534529676.208, "dur": 37.024, + "args": { + "External id": 1417463,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534529718.543, "dur": 3.850, + "args": { + "External id": 1417464,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529720.586, "dur": 0.613, + "args": { + "External id": 1417465,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534529731.187, "dur": 1.596, + "args": { + "External id": 1417466,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534529742.650, "dur": 7.127, + "args": { + "External id": 1417467,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534529744.465, "dur": 4.945, + "args": { + "External id": 1417468,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534529829.417, "dur": 176.162, + "args": { + "External id": 1417469,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534529831.348, "dur": 3.286, + "args": { + "External id": 1417470,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534529836.305, "dur": 168.730, + "args": { + "External id": 1417471,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534529837.743, "dur": 0.269, + "args": { + "External id": 1417472,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534529839.293, "dur": 20.928, + "args": { + "External id": 1417473,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534529864.174, "dur": 2.789, + "args": { + "External id": 1417474,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529866.379, "dur": 0.404, + "args": { + "External id": 1417475,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534529867.856, "dur": 22.194, + "args": { + "External id": 1417476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534529868.850, "dur": 1.191, + "args": { + "External id": 1417477,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534529871.137, "dur": 18.500, + "args": { + "External id": 1417478,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529875.461, "dur": 2.438, + "args": { + "External id": 1417479,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534529891.182, "dur": 18.928, + "args": { + "External id": 1417480,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529911.562, "dur": 12.768, + "args": { + "External id": 1417481,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534529926.645, "dur": 11.459, + "args": { + "External id": 1417482,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529939.414, "dur": 16.539, + "args": { + "External id": 1417483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534529958.150, "dur": 20.040, + "args": { + "External id": 1417484,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529961.977, "dur": 1.647, + "args": { + "External id": 1417485,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534529965.561, "dur": 0.609, + "args": { + "External id": 1417486,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529980.290, "dur": 11.414, + "args": { + "External id": 1417487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534529992.758, "dur": 11.290, + "args": { + "External id": 1417488,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534530012.292, "dur": 1.341, + "args": { + "External id": 1417489,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534530021.298, "dur": 3.699, + "args": { + "External id": 1417490,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530023.727, "dur": 0.429, + "args": { + "External id": 1417491,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534530122.289, "dur": 57.912, + "args": { + "External id": 1417492,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534530187.729, "dur": 5.960, + "args": { + "External id": 1417493,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530191.296, "dur": 0.955, + "args": { + "External id": 1417494,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530195.218, "dur": 27.458, + "args": { + "External id": 1417495,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534530227.398, "dur": 5.806, + "args": { + "External id": 1417496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534530228.914, "dur": 3.585, + "args": { + "External id": 1417497,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530231.249, "dur": 1.038, + "args": { + "External id": 1417498,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534530238.038, "dur": 42.480, + "args": { + "External id": 1417499,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534530239.198, "dur": 40.563, + "args": { + "External id": 1417500,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530284.224, "dur": 17.400, + "args": { + "External id": 1417501,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534530305.630, "dur": 26.671, + "args": { + "External id": 1417502,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534530308.034, "dur": 23.900, + "args": { + "External id": 1417503,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530315.151, "dur": 0.479, + "args": { + "External id": 1417504,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 20324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534530337.507, "dur": 29.028, + "args": { + "External id": 1417505,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 20325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534530339.177, "dur": 27.106, + "args": { + "External id": 1417506,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 20326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530345.507, "dur": 3.538, + "args": { + "External id": 1417507,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530350.363, "dur": 15.417, + "args": { + "External id": 1417508,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534530377.594, "dur": 4.931, + "args": { + "External id": 1417509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534530379.401, "dur": 2.677, + "args": { + "External id": 1417510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534530383.511, "dur": 0.979, + "args": { + "External id": 1417511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534530383.964, "dur": 0.450, + "args": { + "External id": 1417512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530446.717, "dur": 27.555, + "args": { + "External id": 1417513,"Sequence number": 15109287, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530476.384, "dur": 17.835, + "args": { + "External id": 1417514,"Sequence number": 15109288, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20334 + } + }, + { + "ph": "s", "id": 233, "pid": 2338710, "tid": 2338710, "ts": 6410534530476.384, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534530500.157, "dur": 7.261, + "args": { + "External id": 1417515,"Sequence number": 15109289, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 20335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530504.134, "dur": 1.449, + "args": { + "External id": 1417516,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 20336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410534530509.813, "dur": 6.106, + "args": { + "External id": 1417517,"Sequence number": 15109289, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "3"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 20337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530514.101, "dur": 0.587, + "args": { + "External id": 1417518,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 20338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534530517.485, "dur": 4.550, + "args": { + "External id": 1417519,"Sequence number": 15109289, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 20339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530520.987, "dur": 0.461, + "args": { + "External id": 1417520,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 20340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534530527.146, "dur": 5.568, + "args": { + "External id": 1417521,"Sequence number": 15109289, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 20341 + } + }, + { + "ph": "s", "id": 232, "pid": 2338710, "tid": 2338710, "ts": 6410534530527.146, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530530.648, "dur": 0.846, + "args": { + "External id": 1417522,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 20342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534530533.874, "dur": 4.475, + "args": { + "External id": 1417523,"Sequence number": 15109290, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 20343 + } + }, + { + "ph": "s", "id": 231, "pid": 2338710, "tid": 2338710, "ts": 6410534530533.874, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530537.116, "dur": 0.401, + "args": { + "External id": 1417524,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 20344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338710, "tid": 2338710, + "ts": 6410534530541.681, "dur": 5.110, + "args": { + "External id": 1417525,"Sequence number": 15109291, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 20345 + } + }, + { + "ph": "s", "id": 230, "pid": 2338710, "tid": 2338710, "ts": 6410534530541.681, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530545.443, "dur": 0.366, + "args": { + "External id": 1417526,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 20346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534530548.008, "dur": 4.842, + "args": { + "External id": 1417527,"Sequence number": 15109292, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 20347 + } + }, + { + "ph": "s", "id": 229, "pid": 2338710, "tid": 2338710, "ts": 6410534530548.008, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530550.978, "dur": 1.008, + "args": { + "External id": 1417528,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 20348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410534530556.472, "dur": 35.309, + "args": { + "External id": 1417529,"Sequence number": 15109293, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 20349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410534530557.966, "dur": 33.619, + "args": { + "External id": 1417530,"Sequence number": 15109293, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 20350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534530560.841, "dur": 8.444, + "args": { + "External id": 1417531,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 20351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534530563.128, "dur": 5.497, + "args": { + "External id": 1417532,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530572.470, "dur": 18.582, + "args": { + "External id": 1417533,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 20353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534530617.111, "dur": 4.343, + "args": { + "External id": 1417534,"Sequence number": 15109293, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 20354 + } + }, + { + "ph": "s", "id": 228, "pid": 2338710, "tid": 2338710, "ts": 6410534530617.111, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534530623.978, "dur": 1.118, + "args": { + "External id": 1417535,"Sequence number": 15109294, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 20355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338710, "tid": 2338710, + "ts": 6410534530657.298, "dur": 46625.571, + "args": { + "External id": 1417536,"Sequence number": 15109294, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 20356 + } + }, + { + "ph": "s", "id": 227, "pid": 2338710, "tid": 2338710, "ts": 6410534530657.298, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338710, "tid": 2338710, + "ts": 6410534530672.669, "dur": 31.083, + "args": { + "External id": 1417537,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 20357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410534530673.272, "dur": 30.217, + "args": { + "External id": 1417538,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 20358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534530674.908, "dur": 8.437, + "args": { + "External id": 1417539,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 20359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534530678.664, "dur": 4.110, + "args": { + "External id": 1417540,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530684.388, "dur": 18.644, + "args": { + "External id": 1417541,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 20361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534530720.293, "dur": 27.259, + "args": { + "External id": 1417542,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 20362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534530721.410, "dur": 6.331, + "args": { + "External id": 1417543,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 20363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530723.634, "dur": 3.844, + "args": { + "External id": 1417544,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530729.146, "dur": 18.188, + "args": { + "External id": 1417545,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530731.112, "dur": 15.780, + "args": { + "External id": 1417546,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 20366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534530750.864, "dur": 22.178, + "args": { + "External id": 1417547,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 20367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534530751.848, "dur": 4.300, + "args": { + "External id": 1417548,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 20368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530753.312, "dur": 2.602, + "args": { + "External id": 1417549,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530758.857, "dur": 13.987, + "args": { + "External id": 1417550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530759.517, "dur": 13.035, + "args": { + "External id": 1417551,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 20371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410534530779.505, "dur": 18.459, + "args": { + "External id": 1417552,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 20372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534530780.908, "dur": 2.797, + "args": { + "External id": 1417553,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530784.273, "dur": 13.426, + "args": { + "External id": 1417554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 20374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530784.992, "dur": 12.363, + "args": { + "External id": 1417555,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410534530802.274, "dur": 22.561, + "args": { + "External id": 1417556,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534530827.439, "dur": 51.753, + "args": { + "External id": 1417557,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534530831.404, "dur": 47.348, + "args": { + "External id": 1417558,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530835.840, "dur": 2.532, + "args": { + "External id": 1417559,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 20379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534530839.545, "dur": 22.238, + "args": { + "External id": 1417560,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534530840.890, "dur": 20.705, + "args": { + "External id": 1417561,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 20381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534530843.548, "dur": 2.557, + "args": { + "External id": 1417562,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534530847.020, "dur": 14.274, + "args": { + "External id": 1417563,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 20383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410534530883.147, "dur": 40635.507, + "args": { + "External id": 1417564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 20384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410534530884.548, "dur": 40632.011, + "args": { + "External id": 1417565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 20385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534571535.274, "dur": 9.649, + "args": { + "External id": 1417566,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534571540.892, "dur": 1.795, + "args": { + "External id": 1417567,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534571552.826, "dur": 109.888, + "args": { + "External id": 1417568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534571554.245, "dur": 6.773, + "args": { + "External id": 1417569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534571557.074, "dur": 3.053, + "args": { + "External id": 1417570,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534571559.091, "dur": 0.780, + "args": { + "External id": 1417571,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534571562.425, "dur": 99.531, + "args": { + "External id": 1417572,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534571564.434, "dur": 96.644, + "args": { + "External id": 1417573,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534571667.285, "dur": 4.667, + "args": { + "External id": 1417574,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534571669.989, "dur": 0.589, + "args": { + "External id": 1417575,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534571683.904, "dur": 2.843, + "args": { + "External id": 1417576,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534571697.074, "dur": 6.892, + "args": { + "External id": 1417577,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534571699.379, "dur": 4.260, + "args": { + "External id": 1417578,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534571842.547, "dur": 245.473, + "args": { + "External id": 1417579,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534571846.763, "dur": 2.172, + "args": { + "External id": 1417580,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534571852.705, "dur": 234.680, + "args": { + "External id": 1417581,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534571854.470, "dur": 0.637, + "args": { + "External id": 1417582,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534571856.560, "dur": 30.147, + "args": { + "External id": 1417583,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534571888.352, "dur": 5.007, + "args": { + "External id": 1417584,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534571892.163, "dur": 0.871, + "args": { + "External id": 1417585,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534571894.365, "dur": 25.718, + "args": { + "External id": 1417586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534571896.024, "dur": 0.977, + "args": { + "External id": 1417587,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534571898.691, "dur": 21.135, + "args": { + "External id": 1417588,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534571902.449, "dur": 3.454, + "args": { + "External id": 1417589,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534571923.886, "dur": 24.173, + "args": { + "External id": 1417590,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534571949.894, "dur": 18.193, + "args": { + "External id": 1417591,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534571971.380, "dur": 15.907, + "args": { + "External id": 1417592,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534571988.894, "dur": 14.371, + "args": { + "External id": 1417593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534572005.406, "dur": 20.784, + "args": { + "External id": 1417594,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572007.800, "dur": 1.552, + "args": { + "External id": 1417595,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572011.552, "dur": 0.451, + "args": { + "External id": 1417596,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572030.267, "dur": 12.038, + "args": { + "External id": 1417597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572043.657, "dur": 41.542, + "args": { + "External id": 1417598,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534572098.343, "dur": 2.813, + "args": { + "External id": 1417599,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534572108.687, "dur": 4.632, + "args": { + "External id": 1417600,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572111.450, "dur": 0.864, + "args": { + "External id": 1417601,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534572194.195, "dur": 71.037, + "args": { + "External id": 1417602,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534572270.590, "dur": 6.704, + "args": { + "External id": 1417603,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572273.879, "dur": 0.646, + "args": { + "External id": 1417604,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572281.108, "dur": 26.845, + "args": { + "External id": 1417605,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534572313.594, "dur": 6.922, + "args": { + "External id": 1417606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534572315.539, "dur": 4.312, + "args": { + "External id": 1417607,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572317.956, "dur": 1.657, + "args": { + "External id": 1417608,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534572323.400, "dur": 43.859, + "args": { + "External id": 1417609,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534572324.629, "dur": 41.951, + "args": { + "External id": 1417610,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572371.526, "dur": 15.416, + "args": { + "External id": 1417611,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534572395.546, "dur": 3.820, + "args": { + "External id": 1417612,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572398.012, "dur": 0.446, + "args": { + "External id": 1417613,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534572403.700, "dur": 74.753, + "args": { + "External id": 1417614,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534572404.843, "dur": 4.497, + "args": { + "External id": 1417615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534572405.879, "dur": 2.841, + "args": { + "External id": 1417616,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572407.813, "dur": 0.727, + "args": { + "External id": 1417617,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534572428.958, "dur": 48.992, + "args": { + "External id": 1417618,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534572430.450, "dur": 46.819, + "args": { + "External id": 1417619,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534572484.110, "dur": 4.603, + "args": { + "External id": 1417620,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572486.628, "dur": 0.704, + "args": { + "External id": 1417621,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534572495.405, "dur": 1.957, + "args": { + "External id": 1417622,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534572506.610, "dur": 10.542, + "args": { + "External id": 1417623,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534572511.260, "dur": 5.552, + "args": { + "External id": 1417624,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534572616.065, "dur": 182.867, + "args": { + "External id": 1417625,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534572618.493, "dur": 2.394, + "args": { + "External id": 1417626,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534572622.670, "dur": 175.751, + "args": { + "External id": 1417627,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534572624.234, "dur": 0.292, + "args": { + "External id": 1417628,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534572625.901, "dur": 22.677, + "args": { + "External id": 1417629,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534572650.199, "dur": 3.635, + "args": { + "External id": 1417630,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572652.710, "dur": 0.888, + "args": { + "External id": 1417631,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534572657.196, "dur": 22.160, + "args": { + "External id": 1417632,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534572658.335, "dur": 1.202, + "args": { + "External id": 1417633,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534572660.515, "dur": 18.505, + "args": { + "External id": 1417634,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572664.954, "dur": 2.666, + "args": { + "External id": 1417635,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534572680.931, "dur": 22.645, + "args": { + "External id": 1417636,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572705.334, "dur": 13.416, + "args": { + "External id": 1417637,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534572721.359, "dur": 12.761, + "args": { + "External id": 1417638,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572735.676, "dur": 12.767, + "args": { + "External id": 1417639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534572750.345, "dur": 21.238, + "args": { + "External id": 1417640,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572752.576, "dur": 1.440, + "args": { + "External id": 1417641,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572758.079, "dur": 0.624, + "args": { + "External id": 1417642,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572773.297, "dur": 12.370, + "args": { + "External id": 1417643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572786.818, "dur": 10.601, + "args": { + "External id": 1417644,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534572805.626, "dur": 1.856, + "args": { + "External id": 1417645,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534572816.065, "dur": 3.697, + "args": { + "External id": 1417646,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572818.451, "dur": 0.496, + "args": { + "External id": 1417647,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534572885.527, "dur": 51.414, + "args": { + "External id": 1417648,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534572941.741, "dur": 7.839, + "args": { + "External id": 1417649,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572947.514, "dur": 0.977, + "args": { + "External id": 1417650,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534572951.089, "dur": 24.494, + "args": { + "External id": 1417651,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534572979.748, "dur": 5.089, + "args": { + "External id": 1417652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534572981.278, "dur": 2.953, + "args": { + "External id": 1417653,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534572983.190, "dur": 0.886, + "args": { + "External id": 1417654,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534572987.141, "dur": 43.197, + "args": { + "External id": 1417655,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534572990.416, "dur": 39.389, + "args": { + "External id": 1417656,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573034.134, "dur": 13.435, + "args": { + "External id": 1417657,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534573086.992, "dur": 5.468, + "args": { + "External id": 1417658,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573090.228, "dur": 0.947, + "args": { + "External id": 1417659,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534573098.315, "dur": 54.233, + "args": { + "External id": 1417660,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534573099.555, "dur": 7.880, + "args": { + "External id": 1417661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534573100.715, "dur": 6.063, + "args": { + "External id": 1417662,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573104.321, "dur": 2.276, + "args": { + "External id": 1417663,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534573108.276, "dur": 43.781, + "args": { + "External id": 1417664,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534573109.220, "dur": 42.081, + "args": { + "External id": 1417665,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534573157.457, "dur": 4.145, + "args": { + "External id": 1417666,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573159.637, "dur": 0.731, + "args": { + "External id": 1417667,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534573167.809, "dur": 1.544, + "args": { + "External id": 1417668,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534573177.755, "dur": 8.843, + "args": { + "External id": 1417669,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534573181.841, "dur": 4.478, + "args": { + "External id": 1417670,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534573276.792, "dur": 218.777, + "args": { + "External id": 1417671,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534573279.222, "dur": 1.700, + "args": { + "External id": 1417672,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534573282.611, "dur": 212.449, + "args": { + "External id": 1417673,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534573284.111, "dur": 0.534, + "args": { + "External id": 1417674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534573288.121, "dur": 21.104, + "args": { + "External id": 1417675,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534573310.750, "dur": 3.319, + "args": { + "External id": 1417676,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573313.363, "dur": 0.480, + "args": { + "External id": 1417677,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534573317.197, "dur": 25.294, + "args": { + "External id": 1417678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534573318.242, "dur": 2.863, + "args": { + "External id": 1417679,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534573322.415, "dur": 19.780, + "args": { + "External id": 1417680,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573325.142, "dur": 3.068, + "args": { + "External id": 1417681,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534573343.943, "dur": 18.919, + "args": { + "External id": 1417682,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573364.555, "dur": 14.764, + "args": { + "External id": 1417683,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534573382.117, "dur": 15.013, + "args": { + "External id": 1417684,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573398.348, "dur": 14.453, + "args": { + "External id": 1417685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534573430.643, "dur": 27.617, + "args": { + "External id": 1417686,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573435.453, "dur": 2.207, + "args": { + "External id": 1417687,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573440.391, "dur": 0.841, + "args": { + "External id": 1417688,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573459.889, "dur": 19.954, + "args": { + "External id": 1417689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573481.119, "dur": 12.704, + "args": { + "External id": 1417690,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534573503.395, "dur": 2.397, + "args": { + "External id": 1417691,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534573515.508, "dur": 4.115, + "args": { + "External id": 1417692,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573518.350, "dur": 0.477, + "args": { + "External id": 1417693,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534573593.122, "dur": 88.830, + "args": { + "External id": 1417694,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534573686.811, "dur": 5.547, + "args": { + "External id": 1417695,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573690.230, "dur": 1.007, + "args": { + "External id": 1417696,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573693.998, "dur": 32.980, + "args": { + "External id": 1417697,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534573732.207, "dur": 10.145, + "args": { + "External id": 1417698,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534573734.189, "dur": 7.381, + "args": { + "External id": 1417699,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573738.622, "dur": 2.744, + "args": { + "External id": 1417700,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534573747.836, "dur": 47.492, + "args": { + "External id": 1417701,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534573748.835, "dur": 45.784, + "args": { + "External id": 1417702,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534573799.587, "dur": 15.834, + "args": { + "External id": 1417703,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534573821.386, "dur": 4.315, + "args": { + "External id": 1417704,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573824.051, "dur": 0.825, + "args": { + "External id": 1417705,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534573829.683, "dur": 46.721, + "args": { + "External id": 1417706,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534573832.638, "dur": 3.643, + "args": { + "External id": 1417707,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534573833.596, "dur": 2.145, + "args": { + "External id": 1417708,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573835.132, "dur": 0.440, + "args": { + "External id": 1417709,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534573837.039, "dur": 38.990, + "args": { + "External id": 1417710,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534573837.796, "dur": 37.562, + "args": { + "External id": 1417711,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534573880.365, "dur": 3.855, + "args": { + "External id": 1417712,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534573882.344, "dur": 0.625, + "args": { + "External id": 1417713,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534573891.908, "dur": 1.211, + "args": { + "External id": 1417714,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534573901.172, "dur": 9.557, + "args": { + "External id": 1417715,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534573903.436, "dur": 6.949, + "args": { + "External id": 1417716,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534573997.447, "dur": 254.449, + "args": { + "External id": 1417717,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534573999.705, "dur": 1.726, + "args": { + "External id": 1417718,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534574004.996, "dur": 246.241, + "args": { + "External id": 1417719,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534574006.624, "dur": 0.418, + "args": { + "External id": 1417720,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534574008.618, "dur": 21.617, + "args": { + "External id": 1417721,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534574031.725, "dur": 3.238, + "args": { + "External id": 1417722,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574034.010, "dur": 0.729, + "args": { + "External id": 1417723,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534574035.841, "dur": 59.760, + "args": { + "External id": 1417724,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534574037.272, "dur": 1.038, + "args": { + "External id": 1417725,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534574039.401, "dur": 55.473, + "args": { + "External id": 1417726,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574044.157, "dur": 2.161, + "args": { + "External id": 1417727,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534574097.970, "dur": 25.098, + "args": { + "External id": 1417728,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574145.873, "dur": 13.906, + "args": { + "External id": 1417729,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534574164.914, "dur": 14.566, + "args": { + "External id": 1417730,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574180.761, "dur": 14.409, + "args": { + "External id": 1417731,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534574197.504, "dur": 21.610, + "args": { + "External id": 1417732,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574199.434, "dur": 1.894, + "args": { + "External id": 1417733,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574203.457, "dur": 0.484, + "args": { + "External id": 1417734,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574220.750, "dur": 13.413, + "args": { + "External id": 1417735,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574237.705, "dur": 12.351, + "args": { + "External id": 1417736,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534574260.221, "dur": 2.379, + "args": { + "External id": 1417737,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534574272.329, "dur": 3.696, + "args": { + "External id": 1417738,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574274.797, "dur": 0.403, + "args": { + "External id": 1417739,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534574345.695, "dur": 60.653, + "args": { + "External id": 1417740,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534574411.108, "dur": 25.762, + "args": { + "External id": 1417741,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574431.491, "dur": 3.057, + "args": { + "External id": 1417742,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574439.355, "dur": 28.344, + "args": { + "External id": 1417743,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534574473.460, "dur": 7.769, + "args": { + "External id": 1417744,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534574477.202, "dur": 3.289, + "args": { + "External id": 1417745,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574479.551, "dur": 0.754, + "args": { + "External id": 1417746,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534574484.618, "dur": 47.619, + "args": { + "External id": 1417747,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534574485.665, "dur": 45.847, + "args": { + "External id": 1417748,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574536.245, "dur": 14.807, + "args": { + "External id": 1417749,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534574557.448, "dur": 6.604, + "args": { + "External id": 1417750,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574562.643, "dur": 0.562, + "args": { + "External id": 1417751,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534574568.221, "dur": 46.574, + "args": { + "External id": 1417752,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534574569.073, "dur": 3.747, + "args": { + "External id": 1417753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534574569.996, "dur": 2.180, + "args": { + "External id": 1417754,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574571.301, "dur": 0.479, + "args": { + "External id": 1417755,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534574573.728, "dur": 40.741, + "args": { + "External id": 1417756,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534574574.441, "dur": 39.673, + "args": { + "External id": 1417757,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534574619.560, "dur": 3.786, + "args": { + "External id": 1417758,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574621.801, "dur": 0.430, + "args": { + "External id": 1417759,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534574630.991, "dur": 1.809, + "args": { + "External id": 1417760,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534574641.404, "dur": 6.520, + "args": { + "External id": 1417761,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534574643.864, "dur": 3.765, + "args": { + "External id": 1417762,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534574739.014, "dur": 193.565, + "args": { + "External id": 1417763,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534574741.098, "dur": 3.343, + "args": { + "External id": 1417764,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534574748.989, "dur": 183.008, + "args": { + "External id": 1417765,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534574750.172, "dur": 0.362, + "args": { + "External id": 1417766,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534574751.626, "dur": 20.784, + "args": { + "External id": 1417767,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534574773.825, "dur": 5.437, + "args": { + "External id": 1417768,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574778.502, "dur": 0.556, + "args": { + "External id": 1417769,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534574780.177, "dur": 22.617, + "args": { + "External id": 1417770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534574781.061, "dur": 1.083, + "args": { + "External id": 1417771,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534574783.073, "dur": 19.443, + "args": { + "External id": 1417772,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574785.738, "dur": 2.854, + "args": { + "External id": 1417773,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534574806.258, "dur": 21.205, + "args": { + "External id": 1417774,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574828.861, "dur": 15.488, + "args": { + "External id": 1417775,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534574847.161, "dur": 13.797, + "args": { + "External id": 1417776,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574862.199, "dur": 13.573, + "args": { + "External id": 1417777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534574878.117, "dur": 22.504, + "args": { + "External id": 1417778,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574881.985, "dur": 1.067, + "args": { + "External id": 1417779,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574885.561, "dur": 0.481, + "args": { + "External id": 1417780,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574904.779, "dur": 12.986, + "args": { + "External id": 1417781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534574919.154, "dur": 11.841, + "args": { + "External id": 1417782,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534574938.471, "dur": 1.683, + "args": { + "External id": 1417783,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534574948.352, "dur": 3.862, + "args": { + "External id": 1417784,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534574950.805, "dur": 0.535, + "args": { + "External id": 1417785,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534575015.182, "dur": 87.653, + "args": { + "External id": 1417786,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534575110.217, "dur": 6.603, + "args": { + "External id": 1417787,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575114.053, "dur": 1.236, + "args": { + "External id": 1417788,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575120.766, "dur": 29.297, + "args": { + "External id": 1417789,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534575155.252, "dur": 17.078, + "args": { + "External id": 1417790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534575162.099, "dur": 9.420, + "args": { + "External id": 1417791,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575168.379, "dur": 2.929, + "args": { + "External id": 1417792,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534575175.408, "dur": 46.193, + "args": { + "External id": 1417793,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534575176.858, "dur": 44.075, + "args": { + "External id": 1417794,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575227.455, "dur": 14.282, + "args": { + "External id": 1417795,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534575248.211, "dur": 3.122, + "args": { + "External id": 1417796,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575250.188, "dur": 0.392, + "args": { + "External id": 1417797,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534575255.299, "dur": 51.858, + "args": { + "External id": 1417798,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534575256.076, "dur": 6.278, + "args": { + "External id": 1417799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534575256.896, "dur": 4.880, + "args": { + "External id": 1417800,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575260.957, "dur": 0.660, + "args": { + "External id": 1417801,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534575263.085, "dur": 43.681, + "args": { + "External id": 1417802,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534575263.847, "dur": 42.160, + "args": { + "External id": 1417803,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534575311.357, "dur": 3.667, + "args": { + "External id": 1417804,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575313.505, "dur": 0.345, + "args": { + "External id": 1417805,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534575320.871, "dur": 1.601, + "args": { + "External id": 1417806,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534575332.759, "dur": 8.077, + "args": { + "External id": 1417807,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534575335.235, "dur": 5.341, + "args": { + "External id": 1417808,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534575446.021, "dur": 180.352, + "args": { + "External id": 1417809,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534575448.565, "dur": 3.110, + "args": { + "External id": 1417810,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534575455.765, "dur": 170.121, + "args": { + "External id": 1417811,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534575457.198, "dur": 0.501, + "args": { + "External id": 1417812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534575459.067, "dur": 21.952, + "args": { + "External id": 1417813,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534575485.017, "dur": 5.017, + "args": { + "External id": 1417814,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575487.364, "dur": 2.389, + "args": { + "External id": 1417815,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534575491.133, "dur": 20.165, + "args": { + "External id": 1417816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534575491.999, "dur": 1.007, + "args": { + "External id": 1417817,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534575494.384, "dur": 16.658, + "args": { + "External id": 1417818,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575497.135, "dur": 2.564, + "args": { + "External id": 1417819,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534575512.573, "dur": 20.657, + "args": { + "External id": 1417820,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575534.453, "dur": 12.240, + "args": { + "External id": 1417821,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534575549.357, "dur": 13.177, + "args": { + "External id": 1417822,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575563.875, "dur": 11.646, + "args": { + "External id": 1417823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534575577.482, "dur": 22.715, + "args": { + "External id": 1417824,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575581.568, "dur": 1.170, + "args": { + "External id": 1417825,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575585.114, "dur": 2.181, + "args": { + "External id": 1417826,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575601.583, "dur": 11.152, + "args": { + "External id": 1417827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575613.954, "dur": 10.852, + "args": { + "External id": 1417828,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534575633.221, "dur": 2.257, + "args": { + "External id": 1417829,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534575643.555, "dur": 3.753, + "args": { + "External id": 1417830,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575645.976, "dur": 0.495, + "args": { + "External id": 1417831,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534575713.000, "dur": 54.709, + "args": { + "External id": 1417832,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534575774.462, "dur": 4.497, + "args": { + "External id": 1417833,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575777.265, "dur": 0.623, + "args": { + "External id": 1417834,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575780.329, "dur": 23.446, + "args": { + "External id": 1417835,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534575807.929, "dur": 5.512, + "args": { + "External id": 1417836,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534575809.453, "dur": 3.295, + "args": { + "External id": 1417837,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575811.429, "dur": 1.033, + "args": { + "External id": 1417838,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534575818.006, "dur": 41.774, + "args": { + "External id": 1417839,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534575819.073, "dur": 39.814, + "args": { + "External id": 1417840,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534575863.416, "dur": 13.123, + "args": { + "External id": 1417841,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534575881.986, "dur": 3.825, + "args": { + "External id": 1417842,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575884.226, "dur": 0.652, + "args": { + "External id": 1417843,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534575889.637, "dur": 45.255, + "args": { + "External id": 1417844,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534575890.650, "dur": 6.096, + "args": { + "External id": 1417845,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534575893.773, "dur": 2.408, + "args": { + "External id": 1417846,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575895.456, "dur": 0.558, + "args": { + "External id": 1417847,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534575897.458, "dur": 37.106, + "args": { + "External id": 1417848,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534575898.253, "dur": 35.642, + "args": { + "External id": 1417849,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534575938.740, "dur": 5.377, + "args": { + "External id": 1417850,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534575940.701, "dur": 2.245, + "args": { + "External id": 1417851,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534575949.503, "dur": 1.370, + "args": { + "External id": 1417852,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534575960.200, "dur": 5.075, + "args": { + "External id": 1417853,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534575962.135, "dur": 2.838, + "args": { + "External id": 1417854,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534576040.929, "dur": 215.131, + "args": { + "External id": 1417855,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534576044.617, "dur": 1.609, + "args": { + "External id": 1417856,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534576047.644, "dur": 207.934, + "args": { + "External id": 1417857,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534576048.848, "dur": 0.472, + "args": { + "External id": 1417858,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534576050.191, "dur": 54.677, + "args": { + "External id": 1417859,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534576109.817, "dur": 5.217, + "args": { + "External id": 1417860,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576113.735, "dur": 0.991, + "args": { + "External id": 1417861,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534576116.251, "dur": 21.266, + "args": { + "External id": 1417862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534576117.638, "dur": 1.450, + "args": { + "External id": 1417863,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534576120.207, "dur": 16.956, + "args": { + "External id": 1417864,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576123.080, "dur": 2.908, + "args": { + "External id": 1417865,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534576138.791, "dur": 20.042, + "args": { + "External id": 1417866,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576160.113, "dur": 15.141, + "args": { + "External id": 1417867,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534576178.098, "dur": 12.429, + "args": { + "External id": 1417868,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576194.161, "dur": 12.400, + "args": { + "External id": 1417869,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534576210.658, "dur": 18.356, + "args": { + "External id": 1417870,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576212.865, "dur": 1.173, + "args": { + "External id": 1417871,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576215.952, "dur": 0.645, + "args": { + "External id": 1417872,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576230.362, "dur": 11.975, + "args": { + "External id": 1417873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576243.526, "dur": 11.006, + "args": { + "External id": 1417874,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534576264.043, "dur": 2.256, + "args": { + "External id": 1417875,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534576276.887, "dur": 3.814, + "args": { + "External id": 1417876,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576279.408, "dur": 0.367, + "args": { + "External id": 1417877,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534576347.307, "dur": 54.832, + "args": { + "External id": 1417878,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534576407.057, "dur": 4.864, + "args": { + "External id": 1417879,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576410.154, "dur": 0.709, + "args": { + "External id": 1417880,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576413.204, "dur": 41.591, + "args": { + "External id": 1417881,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534576461.186, "dur": 9.422, + "args": { + "External id": 1417882,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534576462.654, "dur": 7.010, + "args": { + "External id": 1417883,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576467.253, "dur": 2.193, + "args": { + "External id": 1417884,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534576473.543, "dur": 45.302, + "args": { + "External id": 1417885,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534576474.373, "dur": 43.928, + "args": { + "External id": 1417886,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576522.621, "dur": 14.065, + "args": { + "External id": 1417887,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534576542.861, "dur": 4.227, + "args": { + "External id": 1417888,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576545.566, "dur": 0.650, + "args": { + "External id": 1417889,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338710, "tid": 2338710, + "ts": 6410534576553.074, "dur": 43.038, + "args": { + "External id": 1417890,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534576553.825, "dur": 3.301, + "args": { + "External id": 1417891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534576554.556, "dur": 2.050, + "args": { + "External id": 1417892,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576556.119, "dur": 0.316, + "args": { + "External id": 1417893,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534576558.055, "dur": 37.714, + "args": { + "External id": 1417894,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534576558.547, "dur": 36.554, + "args": { + "External id": 1417895,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534576602.361, "dur": 3.394, + "args": { + "External id": 1417896,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576604.061, "dur": 0.542, + "args": { + "External id": 1417897,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534576611.433, "dur": 1.569, + "args": { + "External id": 1417898,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534576620.590, "dur": 6.281, + "args": { + "External id": 1417899,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534576622.597, "dur": 3.992, + "args": { + "External id": 1417900,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534576716.337, "dur": 173.354, + "args": { + "External id": 1417901,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534576718.332, "dur": 3.135, + "args": { + "External id": 1417902,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338710, "tid": 2338710, + "ts": 6410534576724.615, "dur": 164.644, + "args": { + "External id": 1417903,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338710, "tid": 2338710, + "ts": 6410534576726.033, "dur": 0.438, + "args": { + "External id": 1417904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338710, "tid": 2338710, + "ts": 6410534576727.953, "dur": 19.292, + "args": { + "External id": 1417905,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338710, "tid": 2338710, + "ts": 6410534576748.846, "dur": 4.676, + "args": { + "External id": 1417906,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576751.062, "dur": 2.211, + "args": { + "External id": 1417907,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534576754.397, "dur": 22.539, + "args": { + "External id": 1417908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410534576755.440, "dur": 0.999, + "args": { + "External id": 1417909,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410534576757.322, "dur": 19.366, + "args": { + "External id": 1417910,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576762.016, "dur": 2.708, + "args": { + "External id": 1417911,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410534576778.370, "dur": 18.065, + "args": { + "External id": 1417912,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576797.797, "dur": 12.038, + "args": { + "External id": 1417913,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338710, "tid": 2338710, + "ts": 6410534576812.286, "dur": 12.885, + "args": { + "External id": 1417914,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576826.429, "dur": 11.944, + "args": { + "External id": 1417915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534576840.082, "dur": 18.260, + "args": { + "External id": 1417916,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576842.149, "dur": 1.295, + "args": { + "External id": 1417917,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576845.305, "dur": 0.563, + "args": { + "External id": 1417918,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576862.099, "dur": 10.852, + "args": { + "External id": 1417919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534576874.051, "dur": 14.132, + "args": { + "External id": 1417920,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410534576896.294, "dur": 1.412, + "args": { + "External id": 1417921,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534576905.075, "dur": 3.682, + "args": { + "External id": 1417922,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534576907.521, "dur": 0.453, + "args": { + "External id": 1417923,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534576972.203, "dur": 48.829, + "args": { + "External id": 1417924,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338710, "tid": 2338710, + "ts": 6410534577025.603, "dur": 5.719, + "args": { + "External id": 1417925,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534577028.289, "dur": 1.845, + "args": { + "External id": 1417926,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534577032.748, "dur": 57.399, + "args": { + "External id": 1417927,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338710, "tid": 2338710, + "ts": 6410534577099.449, "dur": 6.122, + "args": { + "External id": 1417928,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338710, "tid": 2338710, + "ts": 6410534577101.113, "dur": 3.570, + "args": { + "External id": 1417929,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534577103.365, "dur": 1.127, + "args": { + "External id": 1417930,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338710, "tid": 2338710, + "ts": 6410534577108.680, "dur": 46.803, + "args": { + "External id": 1417931,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338710, "tid": 2338710, + "ts": 6410534577109.961, "dur": 44.912, + "args": { + "External id": 1417932,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534577158.849, "dur": 15.913, + "args": { + "External id": 1417933,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534577178.776, "dur": 26.105, + "args": { + "External id": 1417934,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338710, "tid": 2338710, + "ts": 6410534577183.265, "dur": 21.239, + "args": { + "External id": 1417935,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534577188.477, "dur": 0.772, + "args": { + "External id": 1417936,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 20756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410534577210.519, "dur": 28.673, + "args": { + "External id": 1417937,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 20757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338710, "tid": 2338710, + "ts": 6410534577212.651, "dur": 26.290, + "args": { + "External id": 1417938,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 20758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534577217.617, "dur": 3.567, + "args": { + "External id": 1417939,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410534577222.539, "dur": 15.991, + "args": { + "External id": 1417940,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534577250.364, "dur": 4.840, + "args": { + "External id": 1417941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534577252.249, "dur": 2.740, + "args": { + "External id": 1417942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534577256.223, "dur": 3.646, + "args": { + "External id": 1417943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338710, "tid": 2338710, + "ts": 6410534577259.249, "dur": 0.543, + "args": { + "External id": 1417944,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534577305.113, "dur": 24.070, + "args": { + "External id": 1417945,"Sequence number": 15109295, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338710, "tid": 2338710, + "ts": 6410534577330.890, "dur": 14.643, + "args": { + "External id": 1417946,"Sequence number": 15109296, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20766 + } + }, + { + "ph": "s", "id": 226, "pid": 2338710, "tid": 2338710, "ts": 6410534577330.890, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 2338710, "tid": 2338710, + "ts": 6410534577471.266, "dur": 44.211, + "args": { + "External id": 1417947,"Record function id": 0, "Ev Idx": 20767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338710, "tid": 2338710, + "ts": 6410534577621.250, "dur": 43.803, + "args": { + "External id": 1417948,"Sequence number": 15109297, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 20768 + } + }, + { + "ph": "s", "id": 225, "pid": 2338710, "tid": 2338710, "ts": 6410534577621.250, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534577698.132, "dur": 29.527, + "args": { + "External id": 1417949,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 20769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410534577699.791, "dur": 9.341, + "args": { + "External id": 1417950,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 20770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410534577704.149, "dur": 4.355, + "args": { + "External id": 1417951,"Record function id": 0, "Concrete Inputs": ["[1]", "[1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410534577710.725, "dur": 16.657, + "args": { + "External id": 1417952,"Record function id": 0, "Concrete Inputs": ["", "1."], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 20772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338710, "tid": 2338710, + "ts": 6410536646174.070, "dur": 93.795, + "args": { + "External id": 1417953,"Sequence number": 15109298, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 20773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338710, "tid": 2338710, + "ts": 6410536646280.141, "dur": 45.476, + "args": { + "External id": 1417954,"Sequence number": 15109299, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 20774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410536646341.476, "dur": 30.807, + "args": { + "External id": 1417955,"Sequence number": 15109300, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410536646375.972, "dur": 273.325, + "args": { + "External id": 1417956,"Sequence number": 15109301, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[1], [1], []], "Ev Idx": 20776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410536647866.209, "dur": 46.690, + "args": { + "External id": 1417957,"Sequence number": 15109302, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 20777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410536647916.880, "dur": 15.190, + "args": { + "External id": 1417958,"Sequence number": 15109303, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 20778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410536647944.243, "dur": 15.725, + "args": { + "External id": 1417959,"Sequence number": 15109304, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410536647962.361, "dur": 14.422, + "args": { + "External id": 1417960,"Sequence number": 15109305, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[1], [1], []], "Ev Idx": 20780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 2338710, "tid": 2338710, + "ts": 6410536651593.344, "dur": 3981.691, + "args": { + "External id": 1417961,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 20781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 2338710, "tid": 2338710, + "ts": 6410536652270.918, "dur": 1866.573, + "args": { + "External id": 1417962,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 20782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338710, "tid": 2338710, + "ts": 6410536652303.211, "dur": 439.703, + "args": { + "External id": 1417963,"Record function id": 0, "Concrete Inputs": ["[68250]", "6", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 20783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410536652309.814, "dur": 19.010, + "args": { + "External id": 1417964,"Record function id": 0, "Concrete Inputs": ["[68250]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338710, "tid": 2338710, + "ts": 6410536652333.105, "dur": 409.364, + "args": { + "External id": 1417965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[68250]], "Ev Idx": 20785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338710, "tid": 2338710, + "ts": 6410536652341.097, "dur": 400.052, + "args": { + "External id": 1417966,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[68250], []], "Ev Idx": 20786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655609.486, "dur": 3.779, + "args": { + "External id": 1417967,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655615.871, "dur": 0.487, + "args": { + "External id": 1417968,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655617.589, "dur": 0.448, + "args": { + "External id": 1417969,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655619.425, "dur": 0.408, + "args": { + "External id": 1417970,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655620.906, "dur": 0.404, + "args": { + "External id": 1417971,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655622.734, "dur": 0.424, + "args": { + "External id": 1417972,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655624.360, "dur": 0.219, + "args": { + "External id": 1417973,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655627.817, "dur": 0.341, + "args": { + "External id": 1417974,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655629.290, "dur": 0.234, + "args": { + "External id": 1417975,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655630.831, "dur": 0.200, + "args": { + "External id": 1417976,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655632.176, "dur": 0.357, + "args": { + "External id": 1417977,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655633.478, "dur": 0.433, + "args": { + "External id": 1417978,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655634.969, "dur": 0.370, + "args": { + "External id": 1417979,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655636.098, "dur": 0.581, + "args": { + "External id": 1417980,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655637.976, "dur": 0.238, + "args": { + "External id": 1417981,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655642.438, "dur": 0.252, + "args": { + "External id": 1417982,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655643.636, "dur": 0.557, + "args": { + "External id": 1417983,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655645.242, "dur": 0.343, + "args": { + "External id": 1417984,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655646.338, "dur": 0.412, + "args": { + "External id": 1417985,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655647.565, "dur": 0.489, + "args": { + "External id": 1417986,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655648.831, "dur": 0.478, + "args": { + "External id": 1417987,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655650.396, "dur": 0.354, + "args": { + "External id": 1417988,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655651.655, "dur": 0.234, + "args": { + "External id": 1417989,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655654.767, "dur": 0.221, + "args": { + "External id": 1417990,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655655.856, "dur": 0.239, + "args": { + "External id": 1417991,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655657.143, "dur": 0.231, + "args": { + "External id": 1417992,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655658.211, "dur": 0.382, + "args": { + "External id": 1417993,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655659.365, "dur": 0.393, + "args": { + "External id": 1417994,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655660.605, "dur": 0.376, + "args": { + "External id": 1417995,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655661.741, "dur": 0.377, + "args": { + "External id": 1417996,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655663.005, "dur": 0.233, + "args": { + "External id": 1417997,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655666.325, "dur": 0.374, + "args": { + "External id": 1417998,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655667.584, "dur": 0.219, + "args": { + "External id": 1417999,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655669.017, "dur": 0.234, + "args": { + "External id": 1418000,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655670.038, "dur": 0.248, + "args": { + "External id": 1418001,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655671.301, "dur": 0.224, + "args": { + "External id": 1418002,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655672.393, "dur": 0.223, + "args": { + "External id": 1418003,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655673.501, "dur": 0.224, + "args": { + "External id": 1418004,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655674.670, "dur": 0.213, + "args": { + "External id": 1418005,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655677.943, "dur": 0.242, + "args": { + "External id": 1418006,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655679.076, "dur": 0.222, + "args": { + "External id": 1418007,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655680.469, "dur": 0.213, + "args": { + "External id": 1418008,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655682.721, "dur": 0.244, + "args": { + "External id": 1418009,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655683.858, "dur": 0.441, + "args": { + "External id": 1418010,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655685.025, "dur": 0.453, + "args": { + "External id": 1418011,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655686.289, "dur": 0.416, + "args": { + "External id": 1418012,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655687.440, "dur": 0.225, + "args": { + "External id": 1418013,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655690.551, "dur": 0.614, + "args": { + "External id": 1418014,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655691.884, "dur": 0.437, + "args": { + "External id": 1418015,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655693.071, "dur": 0.429, + "args": { + "External id": 1418016,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655694.250, "dur": 0.449, + "args": { + "External id": 1418017,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655695.434, "dur": 0.439, + "args": { + "External id": 1418018,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655696.674, "dur": 0.437, + "args": { + "External id": 1418019,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655698.152, "dur": 0.618, + "args": { + "External id": 1418020,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655699.665, "dur": 0.220, + "args": { + "External id": 1418021,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655703.041, "dur": 0.395, + "args": { + "External id": 1418022,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655704.341, "dur": 0.222, + "args": { + "External id": 1418023,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655705.470, "dur": 0.224, + "args": { + "External id": 1418024,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655706.618, "dur": 0.225, + "args": { + "External id": 1418025,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655707.552, "dur": 0.220, + "args": { + "External id": 1418026,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655708.478, "dur": 0.220, + "args": { + "External id": 1418027,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655709.450, "dur": 0.226, + "args": { + "External id": 1418028,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655710.391, "dur": 0.216, + "args": { + "External id": 1418029,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655713.456, "dur": 0.222, + "args": { + "External id": 1418030,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655714.444, "dur": 0.410, + "args": { + "External id": 1418031,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655715.752, "dur": 0.395, + "args": { + "External id": 1418032,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655716.845, "dur": 0.406, + "args": { + "External id": 1418033,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655717.990, "dur": 0.561, + "args": { + "External id": 1418034,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655719.294, "dur": 0.404, + "args": { + "External id": 1418035,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655720.444, "dur": 0.432, + "args": { + "External id": 1418036,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655721.588, "dur": 0.226, + "args": { + "External id": 1418037,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655725.138, "dur": 0.336, + "args": { + "External id": 1418038,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655726.231, "dur": 0.228, + "args": { + "External id": 1418039,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655727.165, "dur": 0.226, + "args": { + "External id": 1418040,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655728.094, "dur": 0.217, + "args": { + "External id": 1418041,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655729.007, "dur": 0.221, + "args": { + "External id": 1418042,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655729.970, "dur": 0.375, + "args": { + "External id": 1418043,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655732.003, "dur": 0.219, + "args": { + "External id": 1418044,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655732.958, "dur": 0.218, + "args": { + "External id": 1418045,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655735.710, "dur": 0.221, + "args": { + "External id": 1418046,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655736.645, "dur": 0.223, + "args": { + "External id": 1418047,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655737.731, "dur": 0.223, + "args": { + "External id": 1418048,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655738.910, "dur": 0.228, + "args": { + "External id": 1418049,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655740.048, "dur": 0.221, + "args": { + "External id": 1418050,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655741.158, "dur": 0.220, + "args": { + "External id": 1418051,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655742.355, "dur": 0.226, + "args": { + "External id": 1418052,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655743.499, "dur": 0.215, + "args": { + "External id": 1418053,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655746.405, "dur": 0.224, + "args": { + "External id": 1418054,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655747.346, "dur": 0.258, + "args": { + "External id": 1418055,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655748.535, "dur": 0.179, + "args": { + "External id": 1418056,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655749.435, "dur": 0.429, + "args": { + "External id": 1418057,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655750.585, "dur": 0.625, + "args": { + "External id": 1418058,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655751.916, "dur": 0.400, + "args": { + "External id": 1418059,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655753.809, "dur": 0.460, + "args": { + "External id": 1418060,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655755.012, "dur": 0.226, + "args": { + "External id": 1418061,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655758.017, "dur": 0.364, + "args": { + "External id": 1418062,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655759.460, "dur": 0.256, + "args": { + "External id": 1418063,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655760.453, "dur": 0.488, + "args": { + "External id": 1418064,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655761.650, "dur": 0.456, + "args": { + "External id": 1418065,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655762.865, "dur": 0.438, + "args": { + "External id": 1418066,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655764.145, "dur": 0.365, + "args": { + "External id": 1418067,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655765.244, "dur": 0.226, + "args": { + "External id": 1418068,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655766.207, "dur": 0.222, + "args": { + "External id": 1418069,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655768.747, "dur": 0.220, + "args": { + "External id": 1418070,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655769.711, "dur": 0.221, + "args": { + "External id": 1418071,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655770.678, "dur": 0.217, + "args": { + "External id": 1418072,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655771.603, "dur": 0.220, + "args": { + "External id": 1418073,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655772.590, "dur": 0.207, + "args": { + "External id": 1418074,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655773.537, "dur": 0.225, + "args": { + "External id": 1418075,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655774.781, "dur": 0.224, + "args": { + "External id": 1418076,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655775.798, "dur": 0.213, + "args": { + "External id": 1418077,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655779.060, "dur": 0.215, + "args": { + "External id": 1418078,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655779.995, "dur": 0.225, + "args": { + "External id": 1418079,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655780.951, "dur": 0.214, + "args": { + "External id": 1418080,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655781.871, "dur": 0.218, + "args": { + "External id": 1418081,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655782.903, "dur": 0.223, + "args": { + "External id": 1418082,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655783.845, "dur": 0.216, + "args": { + "External id": 1418083,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655784.778, "dur": 0.221, + "args": { + "External id": 1418084,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655785.718, "dur": 0.221, + "args": { + "External id": 1418085,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655788.895, "dur": 0.213, + "args": { + "External id": 1418086,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655790.021, "dur": 0.220, + "args": { + "External id": 1418087,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655791.156, "dur": 0.223, + "args": { + "External id": 1418088,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655792.312, "dur": 0.216, + "args": { + "External id": 1418089,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655793.256, "dur": 0.616, + "args": { + "External id": 1418090,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655794.977, "dur": 0.457, + "args": { + "External id": 1418091,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655796.347, "dur": 0.411, + "args": { + "External id": 1418092,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655797.738, "dur": 0.219, + "args": { + "External id": 1418093,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655800.632, "dur": 0.402, + "args": { + "External id": 1418094,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655801.958, "dur": 0.431, + "args": { + "External id": 1418095,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655803.573, "dur": 0.512, + "args": { + "External id": 1418096,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655804.852, "dur": 0.435, + "args": { + "External id": 1418097,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655806.005, "dur": 0.556, + "args": { + "External id": 1418098,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655807.312, "dur": 0.412, + "args": { + "External id": 1418099,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655808.496, "dur": 0.217, + "args": { + "External id": 1418100,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655809.415, "dur": 0.221, + "args": { + "External id": 1418101,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655812.848, "dur": 0.210, + "args": { + "External id": 1418102,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655814.019, "dur": 0.226, + "args": { + "External id": 1418103,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655815.126, "dur": 0.223, + "args": { + "External id": 1418104,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655816.242, "dur": 0.217, + "args": { + "External id": 1418105,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655817.380, "dur": 0.220, + "args": { + "External id": 1418106,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655818.500, "dur": 0.503, + "args": { + "External id": 1418107,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655819.749, "dur": 0.407, + "args": { + "External id": 1418108,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655820.932, "dur": 0.216, + "args": { + "External id": 1418109,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655823.841, "dur": 0.434, + "args": { + "External id": 1418110,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655825.159, "dur": 0.436, + "args": { + "External id": 1418111,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655826.377, "dur": 0.414, + "args": { + "External id": 1418112,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655827.530, "dur": 0.455, + "args": { + "External id": 1418113,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655828.727, "dur": 0.431, + "args": { + "External id": 1418114,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655830.158, "dur": 0.410, + "args": { + "External id": 1418115,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655831.959, "dur": 0.455, + "args": { + "External id": 1418116,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655833.134, "dur": 0.224, + "args": { + "External id": 1418117,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655836.007, "dur": 0.420, + "args": { + "External id": 1418118,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655837.166, "dur": 0.220, + "args": { + "External id": 1418119,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655838.112, "dur": 0.220, + "args": { + "External id": 1418120,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655839.134, "dur": 0.208, + "args": { + "External id": 1418121,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655840.226, "dur": 0.224, + "args": { + "External id": 1418122,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655842.296, "dur": 0.250, + "args": { + "External id": 1418123,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655843.283, "dur": 0.231, + "args": { + "External id": 1418124,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655844.250, "dur": 0.208, + "args": { + "External id": 1418125,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655847.063, "dur": 0.212, + "args": { + "External id": 1418126,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655848.186, "dur": 0.215, + "args": { + "External id": 1418127,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655849.192, "dur": 0.212, + "args": { + "External id": 1418128,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655850.107, "dur": 0.458, + "args": { + "External id": 1418129,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655851.480, "dur": 0.452, + "args": { + "External id": 1418130,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655852.856, "dur": 0.446, + "args": { + "External id": 1418131,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655854.227, "dur": 0.411, + "args": { + "External id": 1418132,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655855.694, "dur": 0.213, + "args": { + "External id": 1418133,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655858.524, "dur": 0.414, + "args": { + "External id": 1418134,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655859.885, "dur": 0.458, + "args": { + "External id": 1418135,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655861.282, "dur": 0.420, + "args": { + "External id": 1418136,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655862.618, "dur": 0.414, + "args": { + "External id": 1418137,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655863.938, "dur": 0.370, + "args": { + "External id": 1418138,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655865.012, "dur": 0.355, + "args": { + "External id": 1418139,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655866.702, "dur": 0.380, + "args": { + "External id": 1418140,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655867.846, "dur": 0.205, + "args": { + "External id": 1418141,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655871.003, "dur": 0.215, + "args": { + "External id": 1418142,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655871.938, "dur": 0.216, + "args": { + "External id": 1418143,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655872.906, "dur": 0.211, + "args": { + "External id": 1418144,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655873.973, "dur": 0.228, + "args": { + "External id": 1418145,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655874.939, "dur": 0.224, + "args": { + "External id": 1418146,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655875.886, "dur": 0.212, + "args": { + "External id": 1418147,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655876.974, "dur": 0.229, + "args": { + "External id": 1418148,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655877.938, "dur": 0.218, + "args": { + "External id": 1418149,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655881.005, "dur": 0.202, + "args": { + "External id": 1418150,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655882.105, "dur": 0.223, + "args": { + "External id": 1418151,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655883.045, "dur": 0.223, + "args": { + "External id": 1418152,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655884.012, "dur": 0.215, + "args": { + "External id": 1418153,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655884.975, "dur": 0.215, + "args": { + "External id": 1418154,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655885.935, "dur": 0.221, + "args": { + "External id": 1418155,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655886.892, "dur": 0.209, + "args": { + "External id": 1418156,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655889.196, "dur": 0.233, + "args": { + "External id": 1418157,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655892.338, "dur": 0.227, + "args": { + "External id": 1418158,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655893.318, "dur": 0.211, + "args": { + "External id": 1418159,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655894.232, "dur": 0.206, + "args": { + "External id": 1418160,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655895.165, "dur": 0.238, + "args": { + "External id": 1418161,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655896.103, "dur": 0.220, + "args": { + "External id": 1418162,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655897.054, "dur": 0.211, + "args": { + "External id": 1418163,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655898.206, "dur": 0.218, + "args": { + "External id": 1418164,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655899.321, "dur": 0.217, + "args": { + "External id": 1418165,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655903.145, "dur": 0.420, + "args": { + "External id": 1418166,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655904.485, "dur": 0.423, + "args": { + "External id": 1418167,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655907.116, "dur": 0.434, + "args": { + "External id": 1418168,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655908.434, "dur": 0.447, + "args": { + "External id": 1418169,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655910.025, "dur": 0.220, + "args": { + "External id": 1418170,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655910.944, "dur": 0.439, + "args": { + "External id": 1418171,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655912.292, "dur": 0.454, + "args": { + "External id": 1418172,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655913.479, "dur": 0.221, + "args": { + "External id": 1418173,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655916.412, "dur": 0.497, + "args": { + "External id": 1418174,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655917.648, "dur": 0.393, + "args": { + "External id": 1418175,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655918.905, "dur": 0.216, + "args": { + "External id": 1418176,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655920.056, "dur": 0.216, + "args": { + "External id": 1418177,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655921.279, "dur": 0.212, + "args": { + "External id": 1418178,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655922.353, "dur": 0.220, + "args": { + "External id": 1418179,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655923.439, "dur": 0.453, + "args": { + "External id": 1418180,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655924.838, "dur": 0.210, + "args": { + "External id": 1418181,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655927.586, "dur": 0.433, + "args": { + "External id": 1418182,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655928.736, "dur": 0.218, + "args": { + "External id": 1418183,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655929.699, "dur": 0.210, + "args": { + "External id": 1418184,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655930.672, "dur": 0.213, + "args": { + "External id": 1418185,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655931.604, "dur": 0.221, + "args": { + "External id": 1418186,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655932.563, "dur": 0.209, + "args": { + "External id": 1418187,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655933.512, "dur": 0.213, + "args": { + "External id": 1418188,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655934.545, "dur": 0.220, + "args": { + "External id": 1418189,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655938.739, "dur": 0.208, + "args": { + "External id": 1418190,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655939.663, "dur": 0.222, + "args": { + "External id": 1418191,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655940.602, "dur": 0.220, + "args": { + "External id": 1418192,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655941.550, "dur": 0.212, + "args": { + "External id": 1418193,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655942.466, "dur": 0.238, + "args": { + "External id": 1418194,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655943.410, "dur": 0.223, + "args": { + "External id": 1418195,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655944.372, "dur": 0.214, + "args": { + "External id": 1418196,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655945.292, "dur": 0.220, + "args": { + "External id": 1418197,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655948.309, "dur": 0.216, + "args": { + "External id": 1418198,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655949.424, "dur": 0.222, + "args": { + "External id": 1418199,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655950.896, "dur": 0.214, + "args": { + "External id": 1418200,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655951.861, "dur": 0.221, + "args": { + "External id": 1418201,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655952.796, "dur": 0.551, + "args": { + "External id": 1418202,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655954.085, "dur": 0.436, + "args": { + "External id": 1418203,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655955.402, "dur": 0.439, + "args": { + "External id": 1418204,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655956.543, "dur": 0.221, + "args": { + "External id": 1418205,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655959.690, "dur": 0.389, + "args": { + "External id": 1418206,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655960.783, "dur": 0.221, + "args": { + "External id": 1418207,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655961.761, "dur": 0.423, + "args": { + "External id": 1418208,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655962.901, "dur": 0.428, + "args": { + "External id": 1418209,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655964.036, "dur": 0.434, + "args": { + "External id": 1418210,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655965.163, "dur": 0.229, + "args": { + "External id": 1418211,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655966.117, "dur": 0.214, + "args": { + "External id": 1418212,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655967.254, "dur": 0.218, + "args": { + "External id": 1418213,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655970.138, "dur": 0.215, + "args": { + "External id": 1418214,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655971.303, "dur": 0.218, + "args": { + "External id": 1418215,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655972.373, "dur": 0.219, + "args": { + "External id": 1418216,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655974.592, "dur": 0.233, + "args": { + "External id": 1418217,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655975.671, "dur": 0.216, + "args": { + "External id": 1418218,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655976.812, "dur": 0.221, + "args": { + "External id": 1418219,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655977.935, "dur": 0.237, + "args": { + "External id": 1418220,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655979.082, "dur": 0.215, + "args": { + "External id": 1418221,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655981.690, "dur": 0.220, + "args": { + "External id": 1418222,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655982.635, "dur": 0.219, + "args": { + "External id": 1418223,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655983.565, "dur": 0.214, + "args": { + "External id": 1418224,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655984.539, "dur": 0.216, + "args": { + "External id": 1418225,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655985.471, "dur": 0.218, + "args": { + "External id": 1418226,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655986.456, "dur": 0.209, + "args": { + "External id": 1418227,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655987.373, "dur": 0.213, + "args": { + "External id": 1418228,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655988.310, "dur": 0.217, + "args": { + "External id": 1418229,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655991.505, "dur": 0.206, + "args": { + "External id": 1418230,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655992.450, "dur": 0.218, + "args": { + "External id": 1418231,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655993.501, "dur": 0.234, + "args": { + "External id": 1418232,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655994.619, "dur": 0.208, + "args": { + "External id": 1418233,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655995.565, "dur": 0.211, + "args": { + "External id": 1418234,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655996.487, "dur": 0.220, + "args": { + "External id": 1418235,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536655997.996, "dur": 0.215, + "args": { + "External id": 1418236,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536656000.287, "dur": 0.235, + "args": { + "External id": 1418237,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536656003.804, "dur": 0.219, + "args": { + "External id": 1418238,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536656004.787, "dur": 0.207, + "args": { + "External id": 1418239,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338710, "tid": 2338710, + "ts": 6410536656097.484, "dur": 1477.248, + "args": { + "External id": 1418240,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338710, "tid": 2338710, + "ts": 6410536656475.965, "dur": 1007.061, + "args": { + "External id": 1424385,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656484.804, "dur": 11.359, + "args": { + "External id": 1424386,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656491.769, "dur": 3.751, + "args": { + "External id": 1424387,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656496.786, "dur": 1.345, + "args": { + "External id": 1424388,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656497.503, "dur": 0.510, + "args": { + "External id": 1424389,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656498.551, "dur": 3.705, + "args": { + "External id": 1424390,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656500.514, "dur": 1.636, + "args": { + "External id": 1424391,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656502.539, "dur": 0.987, + "args": { + "External id": 1424392,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656502.962, "dur": 0.500, + "args": { + "External id": 1424393,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656503.800, "dur": 2.594, + "args": { + "External id": 1424394,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656505.614, "dur": 0.674, + "args": { + "External id": 1424395,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656506.660, "dur": 2.480, + "args": { + "External id": 1424396,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656508.422, "dur": 0.649, + "args": { + "External id": 1424397,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656511.741, "dur": 1.007, + "args": { + "External id": 1424398,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656512.140, "dur": 0.500, + "args": { + "External id": 1424399,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656512.980, "dur": 2.357, + "args": { + "External id": 1424400,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656514.473, "dur": 0.792, + "args": { + "External id": 1424401,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656515.802, "dur": 2.758, + "args": { + "External id": 1424402,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656517.872, "dur": 0.621, + "args": { + "External id": 1424403,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656518.800, "dur": 0.922, + "args": { + "External id": 1424404,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656519.189, "dur": 0.463, + "args": { + "External id": 1424405,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656520.061, "dur": 3.889, + "args": { + "External id": 1424406,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656521.462, "dur": 2.398, + "args": { + "External id": 1424407,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656524.222, "dur": 0.849, + "args": { + "External id": 1424408,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656524.587, "dur": 0.407, + "args": { + "External id": 1424409,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656525.301, "dur": 2.394, + "args": { + "External id": 1424410,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656526.886, "dur": 0.735, + "args": { + "External id": 1424411,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656528.110, "dur": 2.793, + "args": { + "External id": 1424412,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656530.246, "dur": 0.591, + "args": { + "External id": 1424413,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656533.549, "dur": 1.032, + "args": { + "External id": 1424414,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656533.923, "dur": 0.583, + "args": { + "External id": 1424415,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656535.010, "dur": 2.899, + "args": { + "External id": 1424416,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656536.714, "dur": 1.122, + "args": { + "External id": 1424417,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656538.178, "dur": 2.931, + "args": { + "External id": 1424418,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656540.252, "dur": 0.784, + "args": { + "External id": 1424419,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656541.337, "dur": 1.064, + "args": { + "External id": 1424420,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656541.727, "dur": 0.610, + "args": { + "External id": 1424421,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656542.813, "dur": 3.727, + "args": { + "External id": 1424422,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656544.743, "dur": 1.722, + "args": { + "External id": 1424423,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656546.796, "dur": 1.110, + "args": { + "External id": 1424424,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656547.162, "dur": 0.678, + "args": { + "External id": 1424425,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656548.543, "dur": 2.740, + "args": { + "External id": 1424426,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656550.316, "dur": 0.896, + "args": { + "External id": 1424427,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656551.516, "dur": 2.461, + "args": { + "External id": 1424428,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656553.486, "dur": 0.425, + "args": { + "External id": 1424429,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656556.228, "dur": 1.296, + "args": { + "External id": 1424430,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656556.619, "dur": 0.835, + "args": { + "External id": 1424431,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656557.780, "dur": 2.344, + "args": { + "External id": 1424432,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656559.341, "dur": 0.712, + "args": { + "External id": 1424433,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656560.361, "dur": 2.564, + "args": { + "External id": 1424434,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656562.130, "dur": 0.725, + "args": { + "External id": 1424435,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656563.149, "dur": 1.344, + "args": { + "External id": 1424436,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656563.553, "dur": 0.873, + "args": { + "External id": 1424437,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656564.722, "dur": 3.641, + "args": { + "External id": 1424438,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656566.678, "dur": 1.611, + "args": { + "External id": 1424439,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656568.618, "dur": 1.222, + "args": { + "External id": 1424440,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656568.982, "dur": 0.783, + "args": { + "External id": 1424441,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656570.135, "dur": 2.647, + "args": { + "External id": 1424442,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656572.094, "dur": 0.616, + "args": { + "External id": 1424443,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656573.122, "dur": 2.573, + "args": { + "External id": 1424444,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656575.071, "dur": 0.559, + "args": { + "External id": 1424445,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656578.149, "dur": 1.023, + "args": { + "External id": 1424446,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656578.524, "dur": 0.579, + "args": { + "External id": 1424447,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656579.430, "dur": 2.679, + "args": { + "External id": 1424448,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656581.266, "dur": 0.770, + "args": { + "External id": 1424449,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656582.336, "dur": 2.164, + "args": { + "External id": 1424450,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656583.867, "dur": 0.569, + "args": { + "External id": 1424451,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656584.740, "dur": 1.320, + "args": { + "External id": 1424452,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656585.109, "dur": 0.884, + "args": { + "External id": 1424453,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656586.316, "dur": 3.677, + "args": { + "External id": 1424454,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656588.085, "dur": 1.836, + "args": { + "External id": 1424455,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656590.247, "dur": 1.156, + "args": { + "External id": 1424456,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656590.613, "dur": 0.723, + "args": { + "External id": 1424457,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656591.636, "dur": 3.292, + "args": { + "External id": 1424458,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656593.947, "dur": 0.907, + "args": { + "External id": 1424459,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656595.326, "dur": 2.300, + "args": { + "External id": 1424460,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656597.210, "dur": 0.344, + "args": { + "External id": 1424461,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656599.626, "dur": 0.976, + "args": { + "External id": 1424462,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656600.000, "dur": 0.533, + "args": { + "External id": 1424463,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656600.867, "dur": 2.498, + "args": { + "External id": 1424464,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656602.566, "dur": 0.725, + "args": { + "External id": 1424465,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656603.592, "dur": 2.620, + "args": { + "External id": 1424466,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656605.572, "dur": 0.580, + "args": { + "External id": 1424467,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656606.440, "dur": 1.240, + "args": { + "External id": 1424468,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656606.825, "dur": 0.790, + "args": { + "External id": 1424469,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656607.907, "dur": 4.264, + "args": { + "External id": 1424470,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656609.936, "dur": 2.157, + "args": { + "External id": 1424471,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656612.419, "dur": 0.947, + "args": { + "External id": 1424472,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656612.785, "dur": 0.516, + "args": { + "External id": 1424473,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656613.650, "dur": 2.286, + "args": { + "External id": 1424474,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656615.256, "dur": 0.613, + "args": { + "External id": 1424475,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656616.170, "dur": 2.662, + "args": { + "External id": 1424476,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656618.261, "dur": 0.505, + "args": { + "External id": 1424477,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656621.123, "dur": 1.251, + "args": { + "External id": 1424478,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656621.503, "dur": 0.798, + "args": { + "External id": 1424479,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656622.601, "dur": 2.362, + "args": { + "External id": 1424480,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656624.235, "dur": 0.655, + "args": { + "External id": 1424481,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656625.191, "dur": 2.741, + "args": { + "External id": 1424482,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656627.299, "dur": 0.569, + "args": { + "External id": 1424483,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656628.243, "dur": 1.074, + "args": { + "External id": 1424484,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656628.610, "dur": 0.646, + "args": { + "External id": 1424485,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656629.747, "dur": 2.880, + "args": { + "External id": 1424486,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656631.227, "dur": 1.323, + "args": { + "External id": 1424487,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656632.901, "dur": 1.180, + "args": { + "External id": 1424488,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656633.267, "dur": 0.754, + "args": { + "External id": 1424489,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656634.309, "dur": 3.714, + "args": { + "External id": 1424490,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656636.442, "dur": 1.509, + "args": { + "External id": 1424491,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656638.281, "dur": 2.839, + "args": { + "External id": 1424492,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656640.372, "dur": 0.682, + "args": { + "External id": 1424493,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656643.883, "dur": 0.910, + "args": { + "External id": 1424494,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656644.260, "dur": 0.466, + "args": { + "External id": 1424495,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656645.029, "dur": 4.501, + "args": { + "External id": 1424496,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656647.526, "dur": 1.727, + "args": { + "External id": 1424497,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656649.801, "dur": 1.075, + "args": { + "External id": 1424498,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656650.201, "dur": 0.606, + "args": { + "External id": 1424499,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656651.131, "dur": 1.496, + "args": { + "External id": 1424500,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656651.510, "dur": 1.045, + "args": { + "External id": 1424501,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656652.860, "dur": 4.200, + "args": { + "External id": 1424502,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656656.311, "dur": 0.676, + "args": { + "External id": 1424503,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656657.306, "dur": 1.294, + "args": { + "External id": 1424504,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656657.672, "dur": 0.861, + "args": { + "External id": 1424505,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656658.856, "dur": 3.246, + "args": { + "External id": 1424506,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656661.084, "dur": 0.944, + "args": { + "External id": 1424507,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656662.343, "dur": 2.949, + "args": { + "External id": 1424508,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656664.141, "dur": 1.086, + "args": { + "External id": 1424509,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656667.923, "dur": 1.063, + "args": { + "External id": 1424510,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656668.299, "dur": 0.627, + "args": { + "External id": 1424511,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656669.214, "dur": 2.844, + "args": { + "External id": 1424512,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656670.667, "dur": 1.313, + "args": { + "External id": 1424513,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656672.286, "dur": 1.039, + "args": { + "External id": 1424514,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656672.653, "dur": 0.608, + "args": { + "External id": 1424515,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656673.677, "dur": 1.473, + "args": { + "External id": 1424516,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656674.056, "dur": 1.022, + "args": { + "External id": 1424517,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656675.379, "dur": 3.904, + "args": { + "External id": 1424518,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656678.580, "dur": 0.633, + "args": { + "External id": 1424519,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656679.526, "dur": 1.026, + "args": { + "External id": 1424520,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656679.892, "dur": 0.593, + "args": { + "External id": 1424521,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656680.858, "dur": 2.667, + "args": { + "External id": 1424522,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656682.526, "dur": 0.929, + "args": { + "External id": 1424523,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656683.867, "dur": 2.277, + "args": { + "External id": 1424524,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656685.534, "dur": 0.539, + "args": { + "External id": 1424525,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656688.305, "dur": 1.014, + "args": { + "External id": 1424526,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656688.704, "dur": 0.543, + "args": { + "External id": 1424527,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656689.544, "dur": 3.464, + "args": { + "External id": 1424528,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656691.120, "dur": 1.605, + "args": { + "External id": 1424529,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656693.268, "dur": 0.931, + "args": { + "External id": 1424530,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656693.641, "dur": 0.482, + "args": { + "External id": 1424531,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656694.420, "dur": 1.067, + "args": { + "External id": 1424532,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656694.785, "dur": 0.628, + "args": { + "External id": 1424533,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656695.860, "dur": 4.168, + "args": { + "External id": 1424534,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656699.357, "dur": 0.602, + "args": { + "External id": 1424535,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656700.283, "dur": 1.058, + "args": { + "External id": 1424536,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656700.665, "dur": 0.610, + "args": { + "External id": 1424537,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656701.673, "dur": 2.222, + "args": { + "External id": 1424538,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656703.115, "dur": 0.708, + "args": { + "External id": 1424539,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656704.152, "dur": 1.939, + "args": { + "External id": 1424540,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656705.512, "dur": 0.509, + "args": { + "External id": 1424541,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656708.386, "dur": 1.013, + "args": { + "External id": 1424542,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656708.767, "dur": 0.565, + "args": { + "External id": 1424543,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656709.627, "dur": 3.741, + "args": { + "External id": 1424544,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656711.529, "dur": 1.765, + "args": { + "External id": 1424545,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656713.613, "dur": 1.349, + "args": { + "External id": 1424546,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656713.978, "dur": 0.918, + "args": { + "External id": 1424547,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656715.214, "dur": 1.320, + "args": { + "External id": 1424548,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656715.593, "dur": 0.870, + "args": { + "External id": 1424549,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656716.761, "dur": 4.202, + "args": { + "External id": 1424550,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656720.116, "dur": 0.770, + "args": { + "External id": 1424551,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656721.220, "dur": 1.111, + "args": { + "External id": 1424552,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656721.599, "dur": 0.663, + "args": { + "External id": 1424553,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656722.556, "dur": 2.796, + "args": { + "External id": 1424554,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656724.581, "dur": 0.698, + "args": { + "External id": 1424555,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656725.612, "dur": 2.467, + "args": { + "External id": 1424556,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656727.403, "dur": 0.601, + "args": { + "External id": 1424557,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656731.077, "dur": 1.062, + "args": { + "External id": 1424558,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656731.465, "dur": 0.611, + "args": { + "External id": 1424559,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656732.586, "dur": 3.224, + "args": { + "External id": 1424560,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656734.141, "dur": 1.593, + "args": { + "External id": 1424561,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656736.059, "dur": 1.207, + "args": { + "External id": 1424562,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656736.433, "dur": 0.759, + "args": { + "External id": 1424563,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656737.524, "dur": 1.656, + "args": { + "External id": 1424564,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656738.334, "dur": 0.779, + "args": { + "External id": 1424565,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656739.440, "dur": 4.021, + "args": { + "External id": 1424566,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656742.539, "dur": 0.855, + "args": { + "External id": 1424567,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656743.741, "dur": 2.126, + "args": { + "External id": 1424568,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656745.020, "dur": 0.780, + "args": { + "External id": 1424569,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656746.127, "dur": 2.345, + "args": { + "External id": 1424570,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656747.600, "dur": 0.798, + "args": { + "External id": 1424571,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656748.748, "dur": 2.563, + "args": { + "External id": 1424572,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656750.644, "dur": 0.603, + "args": { + "External id": 1424573,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656753.435, "dur": 2.533, + "args": { + "External id": 1424574,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656755.334, "dur": 0.559, + "args": { + "External id": 1424575,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656756.223, "dur": 2.480, + "args": { + "External id": 1424576,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656756.871, "dur": 1.756, + "args": { + "External id": 1424577,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656758.969, "dur": 1.784, + "args": { + "External id": 1424578,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656760.225, "dur": 0.455, + "args": { + "External id": 1424579,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656761.094, "dur": 1.836, + "args": { + "External id": 1424580,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656761.806, "dur": 1.050, + "args": { + "External id": 1424581,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656763.210, "dur": 3.201, + "args": { + "External id": 1424582,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656765.752, "dur": 0.597, + "args": { + "External id": 1424583,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656766.694, "dur": 1.712, + "args": { + "External id": 1424584,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656767.638, "dur": 0.705, + "args": { + "External id": 1424585,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656768.676, "dur": 1.956, + "args": { + "External id": 1424586,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656769.662, "dur": 0.896, + "args": { + "External id": 1424587,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656770.941, "dur": 3.114, + "args": { + "External id": 1424588,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656773.370, "dur": 0.616, + "args": { + "External id": 1424589,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656776.896, "dur": 1.870, + "args": { + "External id": 1424590,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656778.204, "dur": 0.497, + "args": { + "External id": 1424591,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656779.045, "dur": 2.418, + "args": { + "External id": 1424592,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656779.717, "dur": 1.669, + "args": { + "External id": 1424593,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656781.723, "dur": 2.038, + "args": { + "External id": 1424594,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656783.168, "dur": 0.526, + "args": { + "External id": 1424595,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656784.420, "dur": 1.910, + "args": { + "External id": 1424596,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656785.308, "dur": 0.949, + "args": { + "External id": 1424597,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656786.670, "dur": 3.082, + "args": { + "External id": 1424598,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656788.967, "dur": 0.718, + "args": { + "External id": 1424599,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656790.060, "dur": 1.734, + "args": { + "External id": 1424600,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656791.084, "dur": 0.637, + "args": { + "External id": 1424601,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656792.054, "dur": 1.773, + "args": { + "External id": 1424602,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656793.157, "dur": 0.599, + "args": { + "External id": 1424603,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656794.171, "dur": 2.622, + "args": { + "External id": 1424604,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656796.163, "dur": 0.560, + "args": { + "External id": 1424605,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656799.050, "dur": 2.349, + "args": { + "External id": 1424606,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656800.526, "dur": 0.805, + "args": { + "External id": 1424607,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656801.782, "dur": 2.388, + "args": { + "External id": 1424608,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656802.654, "dur": 1.440, + "args": { + "External id": 1424609,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656804.433, "dur": 1.693, + "args": { + "External id": 1424610,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656805.452, "dur": 0.608, + "args": { + "External id": 1424611,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656806.385, "dur": 1.608, + "args": { + "External id": 1424612,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656807.423, "dur": 0.499, + "args": { + "External id": 1424613,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656808.252, "dur": 3.811, + "args": { + "External id": 1424614,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656811.112, "dur": 0.879, + "args": { + "External id": 1424615,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656812.344, "dur": 1.700, + "args": { + "External id": 1424616,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656813.213, "dur": 0.759, + "args": { + "External id": 1424617,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656814.301, "dur": 2.139, + "args": { + "External id": 1424618,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656815.587, "dur": 0.779, + "args": { + "External id": 1424619,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656816.691, "dur": 3.018, + "args": { + "External id": 1424620,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656818.340, "dur": 1.306, + "args": { + "External id": 1424621,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656821.994, "dur": 2.298, + "args": { + "External id": 1424622,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656823.342, "dur": 0.885, + "args": { + "External id": 1424623,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656824.570, "dur": 2.464, + "args": { + "External id": 1424624,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656825.669, "dur": 1.122, + "args": { + "External id": 1424625,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656827.322, "dur": 1.953, + "args": { + "External id": 1424626,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656828.445, "dur": 0.770, + "args": { + "External id": 1424627,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656829.577, "dur": 1.737, + "args": { + "External id": 1424628,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656830.540, "dur": 0.700, + "args": { + "External id": 1424629,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656831.564, "dur": 3.645, + "args": { + "External id": 1424630,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656834.223, "dur": 0.918, + "args": { + "External id": 1424631,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656835.496, "dur": 1.543, + "args": { + "External id": 1424632,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656836.513, "dur": 0.461, + "args": { + "External id": 1424633,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656837.327, "dur": 2.113, + "args": { + "External id": 1424634,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656838.704, "dur": 0.659, + "args": { + "External id": 1424635,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656839.886, "dur": 2.373, + "args": { + "External id": 1424636,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656841.463, "dur": 0.729, + "args": { + "External id": 1424637,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656844.740, "dur": 1.887, + "args": { + "External id": 1424638,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656845.805, "dur": 0.758, + "args": { + "External id": 1424639,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656846.900, "dur": 2.503, + "args": { + "External id": 1424640,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656847.739, "dur": 1.588, + "args": { + "External id": 1424641,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656849.663, "dur": 1.651, + "args": { + "External id": 1424642,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656850.512, "dur": 0.732, + "args": { + "External id": 1424643,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656851.803, "dur": 1.775, + "args": { + "External id": 1424644,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656852.578, "dur": 0.928, + "args": { + "External id": 1424645,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656853.947, "dur": 3.712, + "args": { + "External id": 1424646,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656856.608, "dur": 0.983, + "args": { + "External id": 1424647,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656857.930, "dur": 1.620, + "args": { + "External id": 1424648,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656858.606, "dur": 0.875, + "args": { + "External id": 1424649,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656859.828, "dur": 1.972, + "args": { + "External id": 1424650,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656861.065, "dur": 0.660, + "args": { + "External id": 1424651,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656862.145, "dur": 2.576, + "args": { + "External id": 1424652,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656864.025, "dur": 0.634, + "args": { + "External id": 1424653,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656867.120, "dur": 2.410, + "args": { + "External id": 1424654,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656868.536, "dur": 0.923, + "args": { + "External id": 1424655,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656869.814, "dur": 2.721, + "args": { + "External id": 1424656,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656870.540, "dur": 1.920, + "args": { + "External id": 1424657,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656872.816, "dur": 1.490, + "args": { + "External id": 1424658,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656873.715, "dur": 0.525, + "args": { + "External id": 1424659,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656874.571, "dur": 1.786, + "args": { + "External id": 1424660,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656875.316, "dur": 0.970, + "args": { + "External id": 1424661,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656876.670, "dur": 2.622, + "args": { + "External id": 1424662,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656878.661, "dur": 0.557, + "args": { + "External id": 1424663,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656879.592, "dur": 1.731, + "args": { + "External id": 1424664,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656880.567, "dur": 0.686, + "args": { + "External id": 1424665,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656881.599, "dur": 1.814, + "args": { + "External id": 1424666,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656882.771, "dur": 0.574, + "args": { + "External id": 1424667,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656883.695, "dur": 3.252, + "args": { + "External id": 1424668,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656886.309, "dur": 0.571, + "args": { + "External id": 1424669,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656889.661, "dur": 2.611, + "args": { + "External id": 1424670,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656891.243, "dur": 0.964, + "args": { + "External id": 1424671,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656892.612, "dur": 2.315, + "args": { + "External id": 1424672,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656893.491, "dur": 1.352, + "args": { + "External id": 1424673,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656895.206, "dur": 2.300, + "args": { + "External id": 1424674,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656896.759, "dur": 0.680, + "args": { + "External id": 1424675,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656897.763, "dur": 1.437, + "args": { + "External id": 1424676,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656898.486, "dur": 0.641, + "args": { + "External id": 1424677,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656899.451, "dur": 3.710, + "args": { + "External id": 1424678,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656902.567, "dur": 0.522, + "args": { + "External id": 1424679,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656903.436, "dur": 1.925, + "args": { + "External id": 1424680,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656904.327, "dur": 0.972, + "args": { + "External id": 1424681,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656905.641, "dur": 2.073, + "args": { + "External id": 1424682,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656906.924, "dur": 0.543, + "args": { + "External id": 1424683,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656907.983, "dur": 2.044, + "args": { + "External id": 1424684,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656909.407, "dur": 0.552, + "args": { + "External id": 1424685,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656912.213, "dur": 2.233, + "args": { + "External id": 1424686,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656913.626, "dur": 0.534, + "args": { + "External id": 1424687,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656914.697, "dur": 2.439, + "args": { + "External id": 1424688,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656915.493, "dur": 1.568, + "args": { + "External id": 1424689,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656917.440, "dur": 1.805, + "args": { + "External id": 1424690,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656918.396, "dur": 0.774, + "args": { + "External id": 1424691,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656919.526, "dur": 1.851, + "args": { + "External id": 1424692,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656920.614, "dur": 0.692, + "args": { + "External id": 1424693,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656921.661, "dur": 3.124, + "args": { + "External id": 1424694,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656923.934, "dur": 0.786, + "args": { + "External id": 1424695,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656925.077, "dur": 1.708, + "args": { + "External id": 1424696,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656925.847, "dur": 0.860, + "args": { + "External id": 1424697,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656927.036, "dur": 1.784, + "args": { + "External id": 1424698,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656928.214, "dur": 0.538, + "args": { + "External id": 1424699,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656929.088, "dur": 2.579, + "args": { + "External id": 1424700,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656931.106, "dur": 0.496, + "args": { + "External id": 1424701,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656934.050, "dur": 1.984, + "args": { + "External id": 1424702,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656935.210, "dur": 0.762, + "args": { + "External id": 1424703,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656936.292, "dur": 2.788, + "args": { + "External id": 1424704,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656937.088, "dur": 1.914, + "args": { + "External id": 1424705,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656939.358, "dur": 1.809, + "args": { + "External id": 1424706,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656940.543, "dur": 0.552, + "args": { + "External id": 1424707,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656941.427, "dur": 1.975, + "args": { + "External id": 1424708,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656942.562, "dur": 0.766, + "args": { + "External id": 1424709,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656943.667, "dur": 2.907, + "args": { + "External id": 1424710,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656945.930, "dur": 0.580, + "args": { + "External id": 1424711,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656946.867, "dur": 1.607, + "args": { + "External id": 1424712,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656947.801, "dur": 0.591, + "args": { + "External id": 1424713,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656948.741, "dur": 1.997, + "args": { + "External id": 1424714,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656949.989, "dur": 0.678, + "args": { + "External id": 1424715,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656951.006, "dur": 2.506, + "args": { + "External id": 1424716,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656952.531, "dur": 0.907, + "args": { + "External id": 1424717,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656955.829, "dur": 2.185, + "args": { + "External id": 1424718,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656957.192, "dur": 0.760, + "args": { + "External id": 1424719,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656958.316, "dur": 2.430, + "args": { + "External id": 1424720,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656959.354, "dur": 1.213, + "args": { + "External id": 1424721,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656961.017, "dur": 1.909, + "args": { + "External id": 1424722,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656962.265, "dur": 0.592, + "args": { + "External id": 1424723,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656963.211, "dur": 1.515, + "args": { + "External id": 1424724,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656964.042, "dur": 0.611, + "args": { + "External id": 1424725,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656964.982, "dur": 3.072, + "args": { + "External id": 1424726,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656967.136, "dur": 0.853, + "args": { + "External id": 1424727,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656968.372, "dur": 1.994, + "args": { + "External id": 1424728,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656969.499, "dur": 0.705, + "args": { + "External id": 1424729,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656970.635, "dur": 2.301, + "args": { + "External id": 1424730,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656972.049, "dur": 0.816, + "args": { + "External id": 1424731,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656973.194, "dur": 2.651, + "args": { + "External id": 1424732,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656974.638, "dur": 1.134, + "args": { + "External id": 1424733,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656978.302, "dur": 1.942, + "args": { + "External id": 1424734,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656979.369, "dur": 0.811, + "args": { + "External id": 1424735,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656980.541, "dur": 2.528, + "args": { + "External id": 1424736,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656981.669, "dur": 1.323, + "args": { + "External id": 1424737,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656983.354, "dur": 2.253, + "args": { + "External id": 1424738,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656984.763, "dur": 0.784, + "args": { + "External id": 1424739,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656985.876, "dur": 2.025, + "args": { + "External id": 1424740,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656987.110, "dur": 0.707, + "args": { + "External id": 1424741,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656988.175, "dur": 3.478, + "args": { + "External id": 1424742,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656990.934, "dur": 0.653, + "args": { + "External id": 1424743,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656991.957, "dur": 1.476, + "args": { + "External id": 1424744,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656992.602, "dur": 0.578, + "args": { + "External id": 1424745,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656993.718, "dur": 2.287, + "args": { + "External id": 1424746,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656994.888, "dur": 1.040, + "args": { + "External id": 1424747,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536656996.297, "dur": 2.430, + "args": { + "External id": 1424748,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536656997.836, "dur": 0.816, + "args": { + "External id": 1424749,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657000.879, "dur": 1.820, + "args": { + "External id": 1424750,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657001.786, "dur": 0.845, + "args": { + "External id": 1424751,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657002.967, "dur": 3.512, + "args": { + "External id": 1424752,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657005.142, "dur": 1.257, + "args": { + "External id": 1424753,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657006.760, "dur": 1.950, + "args": { + "External id": 1424754,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657008.083, "dur": 0.551, + "args": { + "External id": 1424755,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657008.974, "dur": 2.391, + "args": { + "External id": 1424756,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657010.575, "dur": 0.719, + "args": { + "External id": 1424757,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657011.624, "dur": 2.966, + "args": { + "External id": 1424758,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657013.906, "dur": 0.615, + "args": { + "External id": 1424759,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657014.910, "dur": 1.467, + "args": { + "External id": 1424760,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657015.847, "dur": 0.469, + "args": { + "External id": 1424761,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657016.647, "dur": 2.000, + "args": { + "External id": 1424762,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657017.730, "dur": 0.846, + "args": { + "External id": 1424763,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657018.907, "dur": 2.403, + "args": { + "External id": 1424764,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657020.686, "dur": 0.558, + "args": { + "External id": 1424765,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657023.333, "dur": 1.647, + "args": { + "External id": 1424766,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657024.361, "dur": 0.531, + "args": { + "External id": 1424767,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657025.258, "dur": 2.618, + "args": { + "External id": 1424768,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657026.275, "dur": 1.526, + "args": { + "External id": 1424769,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657028.181, "dur": 2.646, + "args": { + "External id": 1424770,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657029.754, "dur": 0.912, + "args": { + "External id": 1424771,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657031.077, "dur": 1.651, + "args": { + "External id": 1424772,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657031.841, "dur": 0.813, + "args": { + "External id": 1424773,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657033.145, "dur": 3.335, + "args": { + "External id": 1424774,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657035.527, "dur": 0.877, + "args": { + "External id": 1424775,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657036.770, "dur": 1.711, + "args": { + "External id": 1424776,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657037.634, "dur": 0.780, + "args": { + "External id": 1424777,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657038.759, "dur": 2.371, + "args": { + "External id": 1424778,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657039.943, "dur": 0.927, + "args": { + "External id": 1424779,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657041.400, "dur": 2.294, + "args": { + "External id": 1424780,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657043.016, "dur": 0.611, + "args": { + "External id": 1424781,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657045.847, "dur": 2.505, + "args": { + "External id": 1424782,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657047.647, "dur": 0.640, + "args": { + "External id": 1424783,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657048.607, "dur": 1.960, + "args": { + "External id": 1424784,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657049.510, "dur": 0.981, + "args": { + "External id": 1424785,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657050.850, "dur": 1.666, + "args": { + "External id": 1424786,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657051.829, "dur": 0.622, + "args": { + "External id": 1424787,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657077.119, "dur": 4.025, + "args": { + "External id": 1424788,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657079.912, "dur": 0.922, + "args": { + "External id": 1424789,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657081.537, "dur": 3.613, + "args": { + "External id": 1424790,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657084.323, "dur": 0.761, + "args": { + "External id": 1424791,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657085.467, "dur": 1.660, + "args": { + "External id": 1424792,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657086.263, "dur": 0.763, + "args": { + "External id": 1424793,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657087.480, "dur": 2.198, + "args": { + "External id": 1424794,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657088.461, "dur": 1.143, + "args": { + "External id": 1424795,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657089.981, "dur": 2.373, + "args": { + "External id": 1424796,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657091.732, "dur": 0.555, + "args": { + "External id": 1424797,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657094.839, "dur": 1.907, + "args": { + "External id": 1424798,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657095.947, "dur": 0.729, + "args": { + "External id": 1424799,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657097.020, "dur": 2.021, + "args": { + "External id": 1424800,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657097.689, "dur": 1.276, + "args": { + "External id": 1424801,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657099.345, "dur": 1.882, + "args": { + "External id": 1424802,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657100.549, "dur": 0.403, + "args": { + "External id": 1424803,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657101.595, "dur": 1.523, + "args": { + "External id": 1424804,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657102.327, "dur": 0.720, + "args": { + "External id": 1424805,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657103.457, "dur": 3.244, + "args": { + "External id": 1424806,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657106.175, "dur": 0.466, + "args": { + "External id": 1424807,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657107.020, "dur": 1.344, + "args": { + "External id": 1424808,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657107.739, "dur": 0.549, + "args": { + "External id": 1424809,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657108.656, "dur": 2.096, + "args": { + "External id": 1424810,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657109.977, "dur": 0.704, + "args": { + "External id": 1424811,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657111.063, "dur": 2.536, + "args": { + "External id": 1424812,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657112.899, "dur": 0.599, + "args": { + "External id": 1424813,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657115.796, "dur": 2.271, + "args": { + "External id": 1424814,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657117.454, "dur": 0.551, + "args": { + "External id": 1424815,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657118.372, "dur": 2.582, + "args": { + "External id": 1424816,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657119.372, "dur": 1.507, + "args": { + "External id": 1424817,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657121.312, "dur": 2.237, + "args": { + "External id": 1424818,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657122.834, "dur": 0.644, + "args": { + "External id": 1424819,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657124.010, "dur": 1.932, + "args": { + "External id": 1424820,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657124.799, "dur": 1.071, + "args": { + "External id": 1424821,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657126.248, "dur": 3.130, + "args": { + "External id": 1424822,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657128.693, "dur": 0.613, + "args": { + "External id": 1424823,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657129.677, "dur": 1.391, + "args": { + "External id": 1424824,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657130.455, "dur": 0.537, + "args": { + "External id": 1424825,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657131.387, "dur": 1.935, + "args": { + "External id": 1424826,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657132.439, "dur": 0.814, + "args": { + "External id": 1424827,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657133.601, "dur": 2.316, + "args": { + "External id": 1424828,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657135.116, "dur": 0.713, + "args": { + "External id": 1424829,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657138.159, "dur": 2.275, + "args": { + "External id": 1424830,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657139.456, "dur": 0.914, + "args": { + "External id": 1424831,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657140.723, "dur": 1.922, + "args": { + "External id": 1424832,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657141.418, "dur": 1.153, + "args": { + "External id": 1424833,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657142.924, "dur": 2.137, + "args": { + "External id": 1424834,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657144.174, "dur": 0.805, + "args": { + "External id": 1424835,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657145.341, "dur": 2.030, + "args": { + "External id": 1424836,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657146.238, "dur": 1.062, + "args": { + "External id": 1424837,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657147.677, "dur": 3.496, + "args": { + "External id": 1424838,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657149.943, "dur": 1.163, + "args": { + "External id": 1424839,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657151.452, "dur": 1.730, + "args": { + "External id": 1424840,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657152.545, "dur": 0.565, + "args": { + "External id": 1424841,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657153.524, "dur": 1.815, + "args": { + "External id": 1424842,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657154.621, "dur": 0.647, + "args": { + "External id": 1424843,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657155.630, "dur": 2.891, + "args": { + "External id": 1424844,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657157.849, "dur": 0.609, + "args": { + "External id": 1424845,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657160.796, "dur": 9.718, + "args": { + "External id": 1424846,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657165.410, "dur": 5.035, + "args": { + "External id": 1424847,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657170.792, "dur": 2.876, + "args": { + "External id": 1424848,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657171.910, "dur": 1.688, + "args": { + "External id": 1424849,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657173.967, "dur": 1.629, + "args": { + "External id": 1424850,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657174.912, "dur": 0.617, + "args": { + "External id": 1424851,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657175.895, "dur": 1.634, + "args": { + "External id": 1424852,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657176.774, "dur": 0.689, + "args": { + "External id": 1424853,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657177.799, "dur": 3.332, + "args": { + "External id": 1424854,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657180.334, "dur": 0.736, + "args": { + "External id": 1424855,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657181.541, "dur": 1.858, + "args": { + "External id": 1424856,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657182.422, "dur": 0.902, + "args": { + "External id": 1424857,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657183.686, "dur": 2.344, + "args": { + "External id": 1424858,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657185.028, "dur": 0.936, + "args": { + "External id": 1424859,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657186.348, "dur": 3.233, + "args": { + "External id": 1424860,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657188.069, "dur": 1.438, + "args": { + "External id": 1424861,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657191.786, "dur": 2.621, + "args": { + "External id": 1424862,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657193.470, "dur": 0.877, + "args": { + "External id": 1424863,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657194.674, "dur": 2.387, + "args": { + "External id": 1424864,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657195.661, "dur": 1.329, + "args": { + "External id": 1424865,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657197.357, "dur": 2.238, + "args": { + "External id": 1424866,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657198.668, "dur": 0.768, + "args": { + "External id": 1424867,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657199.886, "dur": 1.888, + "args": { + "External id": 1424868,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657200.574, "dur": 1.134, + "args": { + "External id": 1424869,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657202.148, "dur": 4.234, + "args": { + "External id": 1424870,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657205.090, "dur": 1.224, + "args": { + "External id": 1424871,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657206.916, "dur": 1.989, + "args": { + "External id": 1424872,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657207.742, "dur": 1.081, + "args": { + "External id": 1424873,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657209.186, "dur": 2.213, + "args": { + "External id": 1424874,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657210.581, "dur": 0.751, + "args": { + "External id": 1424875,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657211.676, "dur": 2.725, + "args": { + "External id": 1424876,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657213.370, "dur": 0.958, + "args": { + "External id": 1424877,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657217.059, "dur": 1.820, + "args": { + "External id": 1424878,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657218.359, "dur": 0.448, + "args": { + "External id": 1424879,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657219.189, "dur": 2.392, + "args": { + "External id": 1424880,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657220.086, "dur": 1.424, + "args": { + "External id": 1424881,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657221.967, "dur": 2.476, + "args": { + "External id": 1424882,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657223.535, "dur": 0.844, + "args": { + "External id": 1424883,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657224.736, "dur": 1.492, + "args": { + "External id": 1424884,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657225.437, "dur": 0.722, + "args": { + "External id": 1424885,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657226.488, "dur": 3.238, + "args": { + "External id": 1424886,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657228.933, "dur": 0.717, + "args": { + "External id": 1424887,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657230.098, "dur": 1.415, + "args": { + "External id": 1424888,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657230.776, "dur": 0.670, + "args": { + "External id": 1424889,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657231.890, "dur": 2.224, + "args": { + "External id": 1424890,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657233.036, "dur": 1.009, + "args": { + "External id": 1424891,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657234.445, "dur": 2.354, + "args": { + "External id": 1424892,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657236.136, "dur": 0.587, + "args": { + "External id": 1424893,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657238.972, "dur": 2.158, + "args": { + "External id": 1424894,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657240.309, "dur": 0.752, + "args": { + "External id": 1424895,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657241.471, "dur": 21.527, + "args": { + "External id": 1424896,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657261.362, "dur": 1.539, + "args": { + "External id": 1424897,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657263.406, "dur": 1.795, + "args": { + "External id": 1424898,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657264.534, "dur": 0.593, + "args": { + "External id": 1424899,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657265.636, "dur": 1.262, + "args": { + "External id": 1424900,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657266.254, "dur": 0.577, + "args": { + "External id": 1424901,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657267.177, "dur": 2.861, + "args": { + "External id": 1424902,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657269.480, "dur": 0.497, + "args": { + "External id": 1424903,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657270.381, "dur": 1.598, + "args": { + "External id": 1424904,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657271.108, "dur": 0.798, + "args": { + "External id": 1424905,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657272.288, "dur": 1.378, + "args": { + "External id": 1424906,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657273.123, "dur": 0.460, + "args": { + "External id": 1424907,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657273.972, "dur": 1.884, + "args": { + "External id": 1424908,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657275.301, "dur": 0.477, + "args": { + "External id": 1424909,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657278.009, "dur": 1.727, + "args": { + "External id": 1424910,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657279.037, "dur": 0.637, + "args": { + "External id": 1424911,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657280.061, "dur": 2.651, + "args": { + "External id": 1424912,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657281.003, "dur": 1.630, + "args": { + "External id": 1424913,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657283.021, "dur": 1.938, + "args": { + "External id": 1424914,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657284.221, "dur": 0.667, + "args": { + "External id": 1424915,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657285.338, "dur": 1.976, + "args": { + "External id": 1424916,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657286.448, "dur": 0.799, + "args": { + "External id": 1424917,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657287.606, "dur": 3.593, + "args": { + "External id": 1424918,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657290.374, "dur": 0.758, + "args": { + "External id": 1424919,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657291.508, "dur": 1.387, + "args": { + "External id": 1424920,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657292.295, "dur": 0.537, + "args": { + "External id": 1424921,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657293.243, "dur": 1.619, + "args": { + "External id": 1424922,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657294.101, "dur": 0.696, + "args": { + "External id": 1424923,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657295.181, "dur": 3.013, + "args": { + "External id": 1424924,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657297.495, "dur": 0.631, + "args": { + "External id": 1424925,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657300.561, "dur": 2.206, + "args": { + "External id": 1424926,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657301.635, "dur": 1.067, + "args": { + "External id": 1424927,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657303.030, "dur": 2.791, + "args": { + "External id": 1424928,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657303.921, "dur": 1.832, + "args": { + "External id": 1424929,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338710, "tid": 2338710, + "ts": 6410536657306.118, "dur": 1.792, + "args": { + "External id": 1424930,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657307.157, "dur": 0.687, + "args": { + "External id": 1424931,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338710, "tid": 2338710, + "ts": 6410536657328.529, "dur": 142.446, + "args": { + "External id": 1424932,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 2338710, "tid": 2338710, + "ts": 6410536657589.134, "dur": 143.845, + "args": { + "External id": 1424933,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[273], [], [], [], []], "Ev Idx": 21609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 2338710, "tid": 2338710, + "ts": 6410536657659.374, "dur": 51.842, + "args": { + "External id": 1424934,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[273], [], [], [], []], "Ev Idx": 21610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338710, "tid": 2338710, + "ts": 6410536657674.658, "dur": 1.264, + "args": { + "External id": 1424935,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Redistribute", "pid": 2338710, "tid": 2338710, + "ts": 6410536658166.423, "dur": 974.960, + "args": { + "External id": 1424936,"Sequence number": 15109306, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "False"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 2338710, "tid": 2338710, + "ts": 6410536658230.408, "dur": 68.993, + "args": { + "External id": 1424937,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536658236.255, "dur": 1.855, + "args": { + "External id": 1424938,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536658240.396, "dur": 0.819, + "args": { + "External id": 1424939,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 21615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 2338710, "tid": 2338710, + "ts": 6410536658377.925, "dur": 382.650, + "args": { + "External id": 1424940,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 21616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338710, "tid": 2338710, + "ts": 6410536658382.179, "dur": 74.152, + "args": { + "External id": 1424941,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338710, "tid": 2338710, + "ts": 6410536658387.502, "dur": 10.821, + "args": { + "External id": 1424942,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 21618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410536658392.030, "dur": 5.167, + "args": { + "External id": 1424943,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 21619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338710, "tid": 2338710, + "ts": 6410536658400.123, "dur": 55.249, + "args": { + "External id": 1424944,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 21620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 2338710, "tid": 2338710, + "ts": 6410536658467.497, "dur": 289.521, + "args": { + "External id": 1424945,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[]], [], [], [], []], "Input Dims": [[[]], [], [], [], []], "Ev Idx": 21621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410536658505.890, "dur": 244.179, + "args": { + "External id": 1424946,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 4, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "4", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 21622, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 2338710, "tid": 2338710, + "ts": 6410536658520.485, "dur": 223.859, + "args": { + "External id": 1424947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 2338710, "tid": 2338710, + "ts": 6410536658835.017, "dur": 261.013, + "args": { + "External id": 1424948,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 2338710, "tid": 2338710, + "ts": 6410536658947.196, "dur": 34.713, + "args": { + "External id": 1424949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338710, "tid": 2338710, + "ts": 6410536658966.859, "dur": 5.428, + "args": { + "External id": 1424950,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "4", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 21626, "In msg nelems": 0, "Rank": 4, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 2338710, "tid": 2338710, + "ts": 6410536659008.845, "dur": 79.258, + "args": { + "External id": 1424951,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536659011.999, "dur": 1.358, + "args": { + "External id": 1424952,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536659014.950, "dur": 0.602, + "args": { + "External id": 1424953,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 21629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_ToTorchTensor", "pid": 2338710, "tid": 2338710, + "ts": 6410536659160.564, "dur": 25.271, + "args": { + "External id": 1424954,"Sequence number": 15109307, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338710, "tid": 2338710, + "ts": 6410536659172.398, "dur": 9.994, + "args": { + "External id": 1424955,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338710, "tid": 2338710, + "ts": 6410536659175.464, "dur": 6.770, + "args": { + "External id": 1424956,"Record function id": 0, "Concrete Inputs": ["", "[]"], "Input type": ["float", "ScalarList"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338710, "tid": 2338710, + "ts": 6410536659547.954, "dur": 37.652, + "args": { + "External id": 1424957,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "double", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 21633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reciprocal", "pid": 2338710, "tid": 2338710, + "ts": 6410536659596.142, "dur": 20.984, + "args": { + "External id": 1424958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mul", "pid": 2338710, "tid": 2338710, + "ts": 6410536659625.102, "dur": 23.415, + "args": { + "External id": 1424959,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "double"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clamp", "pid": 2338710, "tid": 2338710, + "ts": 6410536659662.162, "dur": 24.728, + "args": { + "External id": 1424960,"Record function id": 0, "Concrete Inputs": ["", "", "1."], "Input type": ["float", "", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 21636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536659665.397, "dur": 0.351, + "args": { + "External id": 1424961,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 21637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338710, "tid": 2338710, + "ts": 6410536659703.566, "dur": 0.429, + "args": { + "External id": 1424962,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 2338710, "tid": 2338710, + "ts": 6410536659831.051, "dur": 1107.842, + "args": { + "External id": 1424963,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 2338710, "tid": 2338710, + "ts": 6410536660248.832, "dur": 648.511, + "args": { + "External id": 1424964,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isnan", "pid": 2338710, "tid": 2338710, + "ts": 6410536660990.482, "dur": 33.816, + "args": { + "External id": 1424965,"Sequence number": 15109308, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338710, "tid": 2338710, + "ts": 6410536660994.994, "dur": 28.660, + "args": { + "External id": 1424966,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2338710, + "ts": 6410536661028.853, "dur": 7677.644, + "args": { + "External id": 1424967,"Sequence number": 15109308, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410536661030.762, "dur": 7674.961, + "args": { + "External id": 1424968,"Sequence number": 15109308, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410536661033.340, "dur": 7669.187, + "args": { + "External id": 1424969,"Sequence number": 15109308, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isinf", "pid": 2338710, "tid": 2338710, + "ts": 6410536668725.310, "dur": 102.454, + "args": { + "External id": 1424970,"Sequence number": 15109308, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410536668730.635, "dur": 64.414, + "args": { + "External id": 1424971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338710, "tid": 2338710, + "ts": 6410536668744.543, "dur": 5.963, + "args": { + "External id": 1424972,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 21648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338710, "tid": 2338710, + "ts": 6410536668755.886, "dur": 38.789, + "args": { + "External id": 1424973,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], [1]], "Input Dims": [[], [0]], "Ev Idx": 21649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338710, "tid": 2338710, + "ts": 6410536668763.182, "dur": 4.335, + "args": { + "External id": 1424974,"Record function id": 0, "Concrete Inputs": ["", "[]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 21650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338710, "tid": 2338710, + "ts": 6410536668797.741, "dur": 29.100, + "args": { + "External id": 1424975,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338710, "tid": 2338710, + "ts": 6410536668831.656, "dur": 47.821, + "args": { + "External id": 1424976,"Sequence number": 15109308, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338710, "tid": 2338710, + "ts": 6410536668833.153, "dur": 46.109, + "args": { + "External id": 1424977,"Sequence number": 15109308, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338710, "tid": 2338710, + "ts": 6410536668834.784, "dur": 44.094, + "args": { + "External id": 1424978,"Sequence number": 15109308, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21654 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#OptimizersContainer.step", "pid": 2338710, "tid": 2338710, + "ts": 6410536668929.877, "dur": 5930.726, + "args": { + "External id": 1424979,"Record function id": 0, "Ev Idx": 21655 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 2338710, "tid": 2338710, + "ts": 6410536668975.293, "dur": 5863.130, + "args": { + "External id": 1424980,"Record function id": 0, "Ev Idx": 21656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 2338710, "tid": 2338710, + "ts": 6410536670319.142, "dur": 239.568, + "args": { + "External id": 1424981,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670341.447, "dur": 1.159, + "args": { + "External id": 1424982,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670343.700, "dur": 0.118, + "args": { + "External id": 1424983,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670344.379, "dur": 0.226, + "args": { + "External id": 1424984,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670345.015, "dur": 0.060, + "args": { + "External id": 1424985,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670345.593, "dur": 0.193, + "args": { + "External id": 1424986,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670346.224, "dur": 0.238, + "args": { + "External id": 1424987,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670346.947, "dur": 0.182, + "args": { + "External id": 1424988,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670347.609, "dur": 0.196, + "args": { + "External id": 1424989,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670348.355, "dur": 0.198, + "args": { + "External id": 1424990,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670348.973, "dur": 0.087, + "args": { + "External id": 1424991,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670349.427, "dur": 0.199, + "args": { + "External id": 1424992,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670350.033, "dur": 0.061, + "args": { + "External id": 1424993,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670350.478, "dur": 0.174, + "args": { + "External id": 1424994,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670351.053, "dur": 0.215, + "args": { + "External id": 1424995,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670351.853, "dur": 0.189, + "args": { + "External id": 1424996,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670352.425, "dur": 0.197, + "args": { + "External id": 1424997,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670353.031, "dur": 0.086, + "args": { + "External id": 1424998,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670353.506, "dur": 0.089, + "args": { + "External id": 1424999,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670353.974, "dur": 0.081, + "args": { + "External id": 1425000,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670354.409, "dur": 0.064, + "args": { + "External id": 1425001,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670354.840, "dur": 0.064, + "args": { + "External id": 1425002,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670355.312, "dur": 0.061, + "args": { + "External id": 1425003,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670355.802, "dur": 0.053, + "args": { + "External id": 1425004,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670356.279, "dur": 0.071, + "args": { + "External id": 1425005,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670356.628, "dur": 0.070, + "args": { + "External id": 1425006,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670357.053, "dur": 0.066, + "args": { + "External id": 1425007,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670357.505, "dur": 0.069, + "args": { + "External id": 1425008,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670357.929, "dur": 0.064, + "args": { + "External id": 1425009,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670358.355, "dur": 0.068, + "args": { + "External id": 1425010,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670358.751, "dur": 0.069, + "args": { + "External id": 1425011,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670359.253, "dur": 0.071, + "args": { + "External id": 1425012,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670359.727, "dur": 0.075, + "args": { + "External id": 1425013,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670360.113, "dur": 0.067, + "args": { + "External id": 1425014,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670360.491, "dur": 0.099, + "args": { + "External id": 1425015,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670361.122, "dur": 0.231, + "args": { + "External id": 1425016,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670361.867, "dur": 0.056, + "args": { + "External id": 1425017,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670362.283, "dur": 0.072, + "args": { + "External id": 1425018,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670362.738, "dur": 0.089, + "args": { + "External id": 1425019,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670363.100, "dur": 0.207, + "args": { + "External id": 1425020,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670363.722, "dur": 0.198, + "args": { + "External id": 1425021,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670364.176, "dur": 0.177, + "args": { + "External id": 1425022,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670364.649, "dur": 0.098, + "args": { + "External id": 1425023,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670365.020, "dur": 0.213, + "args": { + "External id": 1425024,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670365.656, "dur": 0.066, + "args": { + "External id": 1425025,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670365.962, "dur": 0.221, + "args": { + "External id": 1425026,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670366.526, "dur": 0.067, + "args": { + "External id": 1425027,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670366.849, "dur": 0.055, + "args": { + "External id": 1425028,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670367.324, "dur": 0.055, + "args": { + "External id": 1425029,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670367.619, "dur": 0.052, + "args": { + "External id": 1425030,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670368.007, "dur": 0.066, + "args": { + "External id": 1425031,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670368.329, "dur": 0.060, + "args": { + "External id": 1425032,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670368.753, "dur": 0.062, + "args": { + "External id": 1425033,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670369.065, "dur": 0.066, + "args": { + "External id": 1425034,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670369.478, "dur": 0.065, + "args": { + "External id": 1425035,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670369.812, "dur": 0.054, + "args": { + "External id": 1425036,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670370.229, "dur": 0.070, + "args": { + "External id": 1425037,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670370.555, "dur": 0.055, + "args": { + "External id": 1425038,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670370.923, "dur": 0.068, + "args": { + "External id": 1425039,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670371.247, "dur": 0.053, + "args": { + "External id": 1425040,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670371.713, "dur": 0.053, + "args": { + "External id": 1425041,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670372.032, "dur": 0.052, + "args": { + "External id": 1425042,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670372.475, "dur": 0.061, + "args": { + "External id": 1425043,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670372.797, "dur": 0.054, + "args": { + "External id": 1425044,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670373.226, "dur": 0.068, + "args": { + "External id": 1425045,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670373.549, "dur": 0.058, + "args": { + "External id": 1425046,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670374.000, "dur": 0.060, + "args": { + "External id": 1425047,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670374.317, "dur": 0.051, + "args": { + "External id": 1425048,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670374.773, "dur": 0.060, + "args": { + "External id": 1425049,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670375.089, "dur": 0.054, + "args": { + "External id": 1425050,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670375.603, "dur": 0.066, + "args": { + "External id": 1425051,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670375.924, "dur": 0.053, + "args": { + "External id": 1425052,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670376.365, "dur": 0.290, + "args": { + "External id": 1425053,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670376.903, "dur": 0.080, + "args": { + "External id": 1425054,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670377.323, "dur": 0.314, + "args": { + "External id": 1425055,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670377.891, "dur": 0.066, + "args": { + "External id": 1425056,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670378.341, "dur": 0.068, + "args": { + "External id": 1425057,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670378.687, "dur": 0.058, + "args": { + "External id": 1425058,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670379.249, "dur": 0.069, + "args": { + "External id": 1425059,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670379.571, "dur": 0.054, + "args": { + "External id": 1425060,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670380.035, "dur": 0.070, + "args": { + "External id": 1425061,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670380.356, "dur": 0.058, + "args": { + "External id": 1425062,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670380.836, "dur": 0.069, + "args": { + "External id": 1425063,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670381.157, "dur": 0.057, + "args": { + "External id": 1425064,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670381.647, "dur": 0.055, + "args": { + "External id": 1425065,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670381.960, "dur": 0.055, + "args": { + "External id": 1425066,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670382.375, "dur": 0.067, + "args": { + "External id": 1425067,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670382.695, "dur": 0.056, + "args": { + "External id": 1425068,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670383.120, "dur": 0.068, + "args": { + "External id": 1425069,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670383.440, "dur": 0.055, + "args": { + "External id": 1425070,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670383.862, "dur": 0.067, + "args": { + "External id": 1425071,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670384.183, "dur": 0.057, + "args": { + "External id": 1425072,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670384.647, "dur": 0.066, + "args": { + "External id": 1425073,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670385.206, "dur": 0.054, + "args": { + "External id": 1425074,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670385.667, "dur": 0.065, + "args": { + "External id": 1425075,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670385.984, "dur": 0.054, + "args": { + "External id": 1425076,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670386.426, "dur": 0.067, + "args": { + "External id": 1425077,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670386.746, "dur": 0.055, + "args": { + "External id": 1425078,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670387.087, "dur": 0.065, + "args": { + "External id": 1425079,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670387.399, "dur": 0.052, + "args": { + "External id": 1425080,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670387.967, "dur": 0.066, + "args": { + "External id": 1425081,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670388.283, "dur": 0.055, + "args": { + "External id": 1425082,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670388.765, "dur": 0.053, + "args": { + "External id": 1425083,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670389.087, "dur": 0.056, + "args": { + "External id": 1425084,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670389.512, "dur": 0.063, + "args": { + "External id": 1425085,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670389.834, "dur": 0.068, + "args": { + "External id": 1425086,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670390.322, "dur": 0.067, + "args": { + "External id": 1425087,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670390.645, "dur": 0.058, + "args": { + "External id": 1425088,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670391.075, "dur": 0.067, + "args": { + "External id": 1425089,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670391.400, "dur": 0.056, + "args": { + "External id": 1425090,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670391.845, "dur": 0.067, + "args": { + "External id": 1425091,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670392.170, "dur": 0.057, + "args": { + "External id": 1425092,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670392.661, "dur": 0.058, + "args": { + "External id": 1425093,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670392.965, "dur": 0.057, + "args": { + "External id": 1425094,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670393.413, "dur": 0.069, + "args": { + "External id": 1425095,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670393.734, "dur": 0.055, + "args": { + "External id": 1425096,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670394.175, "dur": 0.064, + "args": { + "External id": 1425097,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670394.494, "dur": 0.052, + "args": { + "External id": 1425098,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670394.929, "dur": 0.063, + "args": { + "External id": 1425099,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670395.244, "dur": 0.052, + "args": { + "External id": 1425100,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670395.698, "dur": 0.064, + "args": { + "External id": 1425101,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670396.013, "dur": 0.057, + "args": { + "External id": 1425102,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670396.403, "dur": 0.067, + "args": { + "External id": 1425103,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670396.727, "dur": 0.055, + "args": { + "External id": 1425104,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670397.235, "dur": 0.057, + "args": { + "External id": 1425105,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670397.548, "dur": 0.052, + "args": { + "External id": 1425106,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670397.985, "dur": 0.055, + "args": { + "External id": 1425107,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670398.294, "dur": 0.053, + "args": { + "External id": 1425108,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670398.693, "dur": 0.068, + "args": { + "External id": 1425109,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670399.012, "dur": 0.079, + "args": { + "External id": 1425110,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670399.485, "dur": 0.306, + "args": { + "External id": 1425111,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670400.045, "dur": 0.295, + "args": { + "External id": 1425112,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670400.693, "dur": 0.066, + "args": { + "External id": 1425113,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670401.008, "dur": 0.168, + "args": { + "External id": 1425114,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670401.667, "dur": 0.067, + "args": { + "External id": 1425115,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670402.063, "dur": 0.066, + "args": { + "External id": 1425116,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670402.576, "dur": 0.052, + "args": { + "External id": 1425117,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670403.065, "dur": 0.058, + "args": { + "External id": 1425118,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670403.475, "dur": 0.060, + "args": { + "External id": 1425119,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670403.793, "dur": 0.054, + "args": { + "External id": 1425120,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670404.122, "dur": 0.060, + "args": { + "External id": 1425121,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670404.666, "dur": 0.061, + "args": { + "External id": 1425122,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670405.147, "dur": 0.062, + "args": { + "External id": 1425123,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670405.465, "dur": 0.052, + "args": { + "External id": 1425124,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670405.851, "dur": 0.068, + "args": { + "External id": 1425125,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670406.173, "dur": 0.050, + "args": { + "External id": 1425126,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670406.737, "dur": 0.063, + "args": { + "External id": 1425127,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670407.054, "dur": 0.053, + "args": { + "External id": 1425128,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670407.473, "dur": 0.067, + "args": { + "External id": 1425129,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670407.796, "dur": 0.217, + "args": { + "External id": 1425130,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670408.386, "dur": 0.062, + "args": { + "External id": 1425131,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670408.701, "dur": 0.051, + "args": { + "External id": 1425132,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670409.158, "dur": 0.049, + "args": { + "External id": 1425133,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670409.462, "dur": 0.053, + "args": { + "External id": 1425134,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670409.844, "dur": 0.065, + "args": { + "External id": 1425135,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670410.165, "dur": 0.048, + "args": { + "External id": 1425136,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670410.640, "dur": 0.049, + "args": { + "External id": 1425137,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670410.965, "dur": 0.053, + "args": { + "External id": 1425138,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670411.379, "dur": 0.066, + "args": { + "External id": 1425139,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670411.705, "dur": 0.055, + "args": { + "External id": 1425140,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670412.172, "dur": 0.065, + "args": { + "External id": 1425141,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670412.493, "dur": 0.052, + "args": { + "External id": 1425142,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670412.894, "dur": 0.066, + "args": { + "External id": 1425143,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670413.213, "dur": 0.054, + "args": { + "External id": 1425144,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670425.025, "dur": 0.355, + "args": { + "External id": 1425145,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670426.390, "dur": 0.066, + "args": { + "External id": 1425146,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670426.880, "dur": 0.093, + "args": { + "External id": 1425147,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670427.264, "dur": 0.056, + "args": { + "External id": 1425148,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670427.678, "dur": 0.064, + "args": { + "External id": 1425149,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670428.010, "dur": 0.056, + "args": { + "External id": 1425150,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670428.474, "dur": 0.057, + "args": { + "External id": 1425151,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670428.800, "dur": 0.054, + "args": { + "External id": 1425152,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670429.289, "dur": 0.058, + "args": { + "External id": 1425153,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670429.615, "dur": 0.058, + "args": { + "External id": 1425154,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670430.229, "dur": 0.061, + "args": { + "External id": 1425155,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670430.580, "dur": 0.054, + "args": { + "External id": 1425156,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670431.067, "dur": 0.056, + "args": { + "External id": 1425157,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670431.389, "dur": 0.056, + "args": { + "External id": 1425158,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670431.807, "dur": 0.059, + "args": { + "External id": 1425159,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670432.305, "dur": 0.060, + "args": { + "External id": 1425160,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670432.842, "dur": 0.049, + "args": { + "External id": 1425161,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670433.154, "dur": 0.054, + "args": { + "External id": 1425162,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670433.714, "dur": 0.061, + "args": { + "External id": 1425163,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670434.269, "dur": 0.065, + "args": { + "External id": 1425164,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670434.666, "dur": 0.061, + "args": { + "External id": 1425165,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670434.988, "dur": 0.050, + "args": { + "External id": 1425166,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670435.455, "dur": 0.062, + "args": { + "External id": 1425167,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670435.775, "dur": 0.054, + "args": { + "External id": 1425168,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670436.279, "dur": 0.060, + "args": { + "External id": 1425169,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670436.588, "dur": 0.053, + "args": { + "External id": 1425170,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670437.036, "dur": 0.062, + "args": { + "External id": 1425171,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670437.350, "dur": 0.050, + "args": { + "External id": 1425172,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670437.774, "dur": 0.062, + "args": { + "External id": 1425173,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670438.082, "dur": 0.063, + "args": { + "External id": 1425174,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670438.550, "dur": 0.063, + "args": { + "External id": 1425175,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670438.863, "dur": 0.050, + "args": { + "External id": 1425176,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670439.297, "dur": 0.050, + "args": { + "External id": 1425177,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670439.605, "dur": 0.053, + "args": { + "External id": 1425178,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670439.953, "dur": 0.087, + "args": { + "External id": 1425179,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670440.294, "dur": 0.047, + "args": { + "External id": 1425180,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670440.763, "dur": 0.065, + "args": { + "External id": 1425181,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670441.076, "dur": 0.052, + "args": { + "External id": 1425182,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670441.528, "dur": 0.061, + "args": { + "External id": 1425183,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670441.840, "dur": 0.054, + "args": { + "External id": 1425184,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670442.275, "dur": 0.063, + "args": { + "External id": 1425185,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670442.598, "dur": 0.056, + "args": { + "External id": 1425186,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670443.157, "dur": 0.063, + "args": { + "External id": 1425187,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670443.467, "dur": 0.051, + "args": { + "External id": 1425188,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670443.895, "dur": 0.065, + "args": { + "External id": 1425189,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670444.208, "dur": 0.053, + "args": { + "External id": 1425190,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670444.648, "dur": 0.063, + "args": { + "External id": 1425191,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670444.961, "dur": 0.049, + "args": { + "External id": 1425192,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670445.402, "dur": 0.052, + "args": { + "External id": 1425193,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670445.729, "dur": 0.052, + "args": { + "External id": 1425194,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670446.102, "dur": 0.064, + "args": { + "External id": 1425195,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670446.414, "dur": 0.053, + "args": { + "External id": 1425196,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670446.837, "dur": 0.060, + "args": { + "External id": 1425197,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670447.160, "dur": 0.050, + "args": { + "External id": 1425198,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670447.601, "dur": 0.068, + "args": { + "External id": 1425199,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670447.937, "dur": 0.071, + "args": { + "External id": 1425200,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670448.366, "dur": 0.067, + "args": { + "External id": 1425201,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670448.778, "dur": 0.060, + "args": { + "External id": 1425202,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670449.168, "dur": 0.064, + "args": { + "External id": 1425203,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670449.585, "dur": 0.062, + "args": { + "External id": 1425204,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670450.162, "dur": 0.065, + "args": { + "External id": 1425205,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670450.472, "dur": 0.095, + "args": { + "External id": 1425206,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670450.957, "dur": 0.066, + "args": { + "External id": 1425207,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670451.273, "dur": 0.054, + "args": { + "External id": 1425208,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670451.729, "dur": 0.055, + "args": { + "External id": 1425209,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670452.034, "dur": 0.051, + "args": { + "External id": 1425210,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670452.456, "dur": 0.063, + "args": { + "External id": 1425211,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670452.768, "dur": 0.050, + "args": { + "External id": 1425212,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670453.202, "dur": 0.062, + "args": { + "External id": 1425213,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670453.515, "dur": 0.056, + "args": { + "External id": 1425214,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670454.087, "dur": 0.062, + "args": { + "External id": 1425215,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670454.403, "dur": 0.051, + "args": { + "External id": 1425216,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670454.875, "dur": 0.063, + "args": { + "External id": 1425217,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670455.189, "dur": 0.052, + "args": { + "External id": 1425218,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670455.578, "dur": 0.067, + "args": { + "External id": 1425219,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670455.909, "dur": 0.049, + "args": { + "External id": 1425220,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670456.373, "dur": 0.051, + "args": { + "External id": 1425221,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670456.689, "dur": 0.055, + "args": { + "External id": 1425222,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670457.091, "dur": 0.059, + "args": { + "External id": 1425223,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670457.425, "dur": 0.055, + "args": { + "External id": 1425224,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670457.808, "dur": 0.061, + "args": { + "External id": 1425225,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670458.134, "dur": 0.051, + "args": { + "External id": 1425226,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670458.571, "dur": 0.067, + "args": { + "External id": 1425227,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670458.900, "dur": 0.050, + "args": { + "External id": 1425228,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670459.311, "dur": 0.063, + "args": { + "External id": 1425229,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670459.634, "dur": 0.054, + "args": { + "External id": 1425230,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670459.974, "dur": 0.062, + "args": { + "External id": 1425231,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670460.298, "dur": 0.049, + "args": { + "External id": 1425232,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670460.741, "dur": 0.064, + "args": { + "External id": 1425233,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670461.065, "dur": 0.052, + "args": { + "External id": 1425234,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670461.560, "dur": 0.060, + "args": { + "External id": 1425235,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670461.885, "dur": 0.052, + "args": { + "External id": 1425236,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670462.460, "dur": 0.062, + "args": { + "External id": 1425237,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670462.788, "dur": 0.050, + "args": { + "External id": 1425238,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670463.258, "dur": 0.056, + "args": { + "External id": 1425239,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670463.569, "dur": 0.054, + "args": { + "External id": 1425240,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670463.909, "dur": 0.060, + "args": { + "External id": 1425241,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670464.234, "dur": 0.049, + "args": { + "External id": 1425242,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670464.674, "dur": 0.064, + "args": { + "External id": 1425243,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670465.221, "dur": 0.063, + "args": { + "External id": 1425244,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670465.660, "dur": 0.065, + "args": { + "External id": 1425245,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670466.104, "dur": 0.066, + "args": { + "External id": 1425246,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670466.586, "dur": 0.062, + "args": { + "External id": 1425247,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670467.040, "dur": 0.060, + "args": { + "External id": 1425248,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670467.456, "dur": 0.066, + "args": { + "External id": 1425249,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670467.879, "dur": 0.065, + "args": { + "External id": 1425250,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670468.371, "dur": 0.065, + "args": { + "External id": 1425251,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670468.694, "dur": 0.051, + "args": { + "External id": 1425252,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670469.126, "dur": 0.048, + "args": { + "External id": 1425253,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338710, "tid": 2338710, + "ts": 6410536670469.440, "dur": 0.052, + "args": { + "External id": 1425254,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 2338710, "tid": 2338710, + "ts": 6410536671041.005, "dur": 3695.246, + "args": { + "External id": 1425255,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "3.6460270081755531e-06", "0.90000000000000002", "0.94999999999999996", "0.10000000000000001", "1.0000000000000001e-15", "False", "False", "", ""], "Input type": ["TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 21931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 2338710, "tid": 2338710, + "ts": 6410536673523.545, "dur": 1016.688, + "args": { + "External id": 1425256,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "3.6460270081755531e-06", "0.90000000000000002", "0.94999999999999996", "0.10000000000000001", "1.0000000000000001e-15", "False", "False", "", ""], "Input type": ["TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 21932 + } + }, + { + "name": "process_name", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 0, + "args": { + "sort_index": 2338710 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 2379450, + "args": { + "name": "thread 2379450 (pt_autograd_4)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 2379450, + "args": { + "sort_index": 2379450 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 2379450, + "args": { + "name": "thread 2379450 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 2379450, + "args": { + "sort_index": 2379450 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 2338710, + "args": { + "name": "thread 2338710 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6410530220638.123, "pid": 2338710, "tid": 2338710, + "args": { + "sort_index": 2338710 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 6410530220571.748, "dur": 6461100.174, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 6410530220571.748, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 6410530220571.748 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 6410536779820.171 + } + ], + "traceName": "exp/mtp.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine/profile_trace/iteration_32256/rank4_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file